feat(model-router): wave 2-B — orchestrators declare phases, shifters and pins removed, frontmatter = off-state floor

The 15 Skill(effort-*) citers now call mcp__model-router__route per phase (orchestrate at a dispatch span, reflect/plan for the skill's own level, apply at the bookkeeping tail, escalate at the verify-secure caps); built-in judgment dispatches carry an explicit effort= param. lib/effort-shift.md is the route doctrine, lib/model-gate.md the mod rule (route answer = witness, /route on as remedy). Deleted: skills/effort-*, lib/effort-pins.txt/.sh, lib/model-check.sh, their tests, the installers' re-apply blocks. The mod drops its Skill(effort-*) bridge. The tracked model:/effort: frontmatter stays as the off-state floor, census-locked equal to the rows (lib/tests/effort-routing.test.sh rewritten, 140 checks; analyzer → xhigh). Contract .claude/tasks/contracts/2026-10-10-model-router-w2b-1045.md, plan r4 § W2-B: GATE 0 MET, verifier ECARTS(7) then CONFORME 10/10, security PASS, full make test green (design-tool-gate env red only).
2026-10-10 11:24:54 +02:00
parent 65dff0e768
commit 1f2d33b7a6
43 changed files with 318 additions and 811 deletions
@@ -29,7 +29,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 Audit only what changed since the last run, on the axes the user picks.
 Per axis: **audit → approval gate → fix → re-verify → marker update**,
@@ -170,7 +170,7 @@ Then show the user the same compact table inline.

 ### 3b-bis. CHALLENGE THE PROPOSALS (before the gate)

-`Skill(effort-xhigh)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="plan")` first (route: own level before the challenge; send it with the challenger dispatch).
 This axis' findings + proposed fixes are a proposal set worth attacking before
 the human gate. Persist THIS axis' finding list (not the whole append-only
 report) to `.claude/tasks/plans/<date>-<axis>-<HHMM>.md`, then run
@@ -256,7 +256,7 @@ Then offer to capitalize (per CLAUDE.md): recurring finding patterns →
  below on the same delta (the SAST is a deterministic floor, the reasoned
  pass covers what grep/rules miss):
  ```
-  Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+  mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
  Agent(subagent_type="security-auditor", description="audit-delta security — semgrep SAST",
    prompt="MODE: audit\nSCOPE: <delta file list>\nREPORT: .claude/audits/.audit-delta-semgrep.md\nFollow agents/security-auditor.md exactly. Pinned rulesets, no login. Write ONLY to REPORT. End with REPORT_WRITTEN: <path>.")
  ```
@@ -26,7 +26,7 @@ allowed-tools:
 MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE any
 step below. Verdict `small` → STOP — print the gate's remedy, end the
 turn, dispatch nothing.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## REQUEST
 $ARGUMENTS
@@ -119,14 +119,14 @@ RISK: <low/medium — what could go wrong>
  obvious fix.
 - If the fix is significant (>10 lines, multiple files,
  behavior change): wait for user approval.
-  On resume: `Skill(effort-high)` first, sent with the next tool call (effort-shift: turn reset).
+  On resume: `mcp__model-router__route(phase="reflect")` first (route: resumed turn).
 - Then run pass B of `$HOME/.claude/lib/contract-interview.md` against the
  FIX PLAN: every VISIBLE / PUBLIC NAME / SCOPE choice it settles that the
  bug report left open → one batch of questions, before STEP 3b. The trivial
  fast-path is not exempt: a 1-line fix with a visible choice still asks.

 ## STEP 3b — CHALLENGE THE FIX PLAN (before the contract)
-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 Unless the fix is the trivial 1-2 line case STEP 3 already fast-paths, the
 DIAGNOSIS + FIX PLAN is a reflection worth attacking before it hardens into a
 contract. Persist it to `.claude/tasks/plans/<date>-<slug>-<HHMM>.md`, then run
@@ -157,10 +157,10 @@ branch it's a no-op (commit in place). Never `finish`.

 ## STEP 5 — DISPATCH EXECUTOR

-Dispatch the executor — sonnet by frontmatter pin, do not override:
+Dispatch the executor — sonnet by its row (frontmatter = off-state floor), do not override:

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="bugfixer")
 prompt: "CONTRACT: <path from STEP 3.5>
 DIAGNOSIS: <ROOT CAUSE + EVIDENCE from STEP 3>
@@ -282,7 +282,7 @@ A bugfix with an understood root cause is almost always worth one entry:

 If the bug was trivial and the root cause not transferable → skip with `CAPITALIZE: trivial, skip`.

-`Skill(effort-low)` first (effort-shift: bookkeeping tail; send it in the same message as the memory-commit command).
+`mcp__model-router__route(phase="apply")` first (route: bookkeeping tail; send it with the memory-commit command).

 **Then commit the memory** — follow `$HOME/.claude/lib/capitalize-commit.md`: it
 surgically commits what capitalize just wrote (`.claude/memory` + `.claude/tasks`
@@ -26,7 +26,7 @@ allowed-tools:
 MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE any
 step below. Verdict `small` → STOP — print the gate's remedy, end the
 turn, dispatch nothing.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## TARGET
 $ARGUMENTS
@@ -122,7 +122,7 @@ TOTALS: <N blocking, N warn, N info>
 If no issues found: report clean state and stop.

 ## STEP 3b — CHALLENGE THE SCOPE (before approval)
-`Skill(effort-xhigh)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="plan")` first (route: own level before the challenge; send it with the challenger dispatch).
 The STEP 3 report is the proposed cleanup scope — worth attacking before the
 human approves it. It is still inline, so FIRST persist it to
 `.claude/tasks/plans/<date>-<slug>-<HHMM>.md` (STEP 3 report format, one item
@@ -172,10 +172,10 @@ is approved, stop — no dispatch.
   severity — proposed fix`. This is the executor's scope-of-work on
   disk — named, auditable, the same contract discipline as the dev
   gates (verifier reads its contract from disk).
-2. **Dispatch the executor** — sonnet by frontmatter pin, do not override:
+2. **Dispatch the executor** — sonnet by its row (frontmatter = off-state floor), do not override:

   ```
-   Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+   mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
   Agent(subagent_type="code-cleaner")
   prompt: "SCOPE: .claude/audits/CODE-CLEAN-SCOPE.md
   APPROVED: <the approved item list, incl. any per-item exported-symbol clears>
@@ -73,7 +73,7 @@ $ARGUMENTS"

 (`model="opus"` — BDR-077: propose = narrative reconstruction + capitalize
 routing, judgment tier; the call-site override takes precedence over the
-sonnet frontmatter pin. Apply, STEP 4, stays on the pin.)
+sonnet row (frontmatter = off-state floor). Apply, STEP 4, stays on its row.)

 Read the returned `COMMIT PLAN` + `EDGE CASES` + `CAPITALIZE CANDIDATES`,
 terminated by `READY TO APPLY — awaiting dispatcher confirmation`.
@@ -1,6 +0,0 @@
---
-name: effort-high
-description: Investigation shift. Deeper reasoning for diagnosis, LOCATE, contract drafting, refactor judgement inside feat, hotfix and bugfix runs.
-effort: high
---
-Effort shifted to high for the rest of this turn (lib/effort-shift.md). Continue with the caller's next step.
@@ -1,6 +0,0 @@
---
-name: effort-low
-description: Bookkeeping shift. Lowers reasoning to the cheapest level for the rest of the turn: journal lines, memory commits, capitalize, release bookkeeping, status output.
-effort: low
---
-Effort shifted to low for the rest of this turn (lib/effort-shift.md). Continue with the caller's next step.
@@ -1,6 +0,0 @@
---
-name: effort-max
-description: Escalation shift. Maximum reasoning when a verify or security loop hits its cap, a gate fails twice, or error recovery starts in ship-feature.
-effort: max
---
-Effort shifted to max for the rest of this turn (lib/effort-shift.md). Continue with the caller's next step.
@@ -1,6 +0,0 @@
---
-name: effort-medium
-description: Orchestration shift. Standard reasoning between two dispatches: read a subagent report, pick the next step, relay a gate verdict, route a branch.
-effort: medium
---
-Effort shifted to medium for the rest of this turn (lib/effort-shift.md). Continue with the caller's next step.
@@ -1,6 +0,0 @@
---
-name: effort-xhigh
-description: Reflection shift. Deep reasoning for brainstorm, planning, challenge synthesis and audit verdicts before a human validation gate.
-effort: xhigh
---
-Effort shifted to xhigh for the rest of this turn (lib/effort-shift.md). Continue with the caller's next step.
@@ -26,7 +26,7 @@ allowed-tools:
 MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE any
 step below. Verdict `small` → STOP — print the gate's remedy, end the
 turn, dispatch nothing.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## REQUEST
 $ARGUMENTS
@@ -124,7 +124,7 @@ in the contract's CLARIFICATIONS `[gated]` and in the plan. A choice that
 surfaces only during execution comes back as `NEED-DECISION` (STEP 3).

 ## STEP 1b — CHALLENGE THE PLAN (before branching)
-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 The STEP 1 plan is a reflection worth attacking before a branch is spent on it.
 Persist it to `.claude/tasks/plans/<date>-<slug>-<HHMM>.md`, then run
 `$HOME/.claude/lib/challenge-plan.md` with `PLAN` = that file, `KIND` = `build-plan`,
@@ -143,10 +143,10 @@ branch it's a no-op (commit in place). Never `finish`.

 ## STEP 3 — DISPATCH EXECUTOR

-Dispatch the executor — sonnet by frontmatter pin, do not override:
+Dispatch the executor — sonnet by its row (frontmatter = off-state floor), do not override:

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="feater")
 prompt: "CONTRACT: <path from STEP 0.7>
 PLAN: <the STEP 1 checklist + approach bullets + edge cases, verbatim>
@@ -203,7 +203,7 @@ test), consider splitting into 2-3 atomic commits grouped by logical
 unit — or run `/commit-change` on the pending work (it dispatches the
 commit-changer (propose opus / apply sonnet, BDR-077); never inline-load the bare agent, it is now a
 propose/apply executor).
-Then `Skill(effort-high)` (effort-shift: nested commit-change loaded at low; reload feat's level, sent with the next tool call).
+Then `mcp__model-router__route(phase="reflect")` (route: nested commit-change loaded at apply; reload feat's level).

 Print summary:
 ```
@@ -254,7 +254,7 @@ Always append a 1-line entry to today's heading in `.claude/memory/journal.md`.

 If no substantive capture candidate → skip with `CAPITALIZE: nothing to log`.

-`Skill(effort-low)` first (effort-shift: bookkeeping tail; send it in the same message as the memory-commit command).
+`mcp__model-router__route(phase="apply")` first (route: bookkeeping tail; send it with the memory-commit command).

 **Then commit the memory** — follow `$HOME/.claude/lib/capitalize-commit.md`: it
 surgically commits what capitalize just wrote (`.claude/memory` + `.claude/tasks`
@@ -29,7 +29,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 Dispatches the `geo-analyzer` subagent (audit + fix bundle), then applies
 the bundle from THIS main loop at **L1** — same shape as `/web-validate`
@@ -47,7 +47,7 @@ every phase (LRN-126). Clean `.audit/geo-signals-<RUNID>.md` after apply.

 **A — collect (sonnet):**
 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="geo-analyzer", model="sonnet")
 prompt: "MODE: collect
 RUNID: <RUNID>
@@ -86,7 +86,7 @@ your bundle."
 ```

 ## STEP 1b — CHALLENGE THE FIX BUNDLE (advisory, before apply)
-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 The analyzer returned a `## FIX BUNDLE` — worth attacking before any edit lands.
 **Skip if intervention mode = conservative** (nothing is applied). Else persist the
 bundle verbatim to `.claude/tasks/plans/<date>-<slug>-<HHMM>.md`, then run
@@ -118,7 +118,7 @@ intent, not header wording: **AUTO** = no-confirmation items (G1–G4/G6);
 For each AUTO item, dispatch its `applier` at L1, passing the item verbatim:

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="hotfixer")     # or "feater" per the item's applier
 prompt: "<paste the bundle item: files, concern, current, expected,
  framework note + shared-file discipline>.
@@ -29,7 +29,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 This skill orchestrates a narrow-scope hardening audit: TLS + security
 headers + redirects + canonical + custom 404 + server configs. It
@@ -261,7 +261,7 @@ seo-analyzer will run in parallel.
 Spawn a single seo-analyzer subagent with an explicit IN/OUT scope list.

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(
  subagent_type="seo-analyzer",
  description="harden — narrow-scope web hardening audit",
@@ -522,7 +522,7 @@ Extract the score and critical-alert count from `.claude/audits/HARDEN.md` for t
 ---

 ## STEP 2b — CHALLENGE THE FIX BUNDLE (MODE=fix only, advisory)
-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 Skip if MODE=audit (no bundle exists). Else, before the STEP 3 gate, harden the bundle:
 extract the `## 8. Fix bundle` section from HARDEN.md to
 `.claude/tasks/plans/<date>-<slug>-<HHMM>.md` (a clean, blind-judgeable artifact), then run
@@ -24,7 +24,7 @@ allowed-tools:
 MODEL GATE (blocking): run `$HOME/.claude/lib/model-gate.md` BEFORE any
 step below. Verdict `small` → STOP — print the gate's remedy, end the
 turn, dispatch nothing.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## REQUEST
 $ARGUMENTS
@@ -94,7 +94,7 @@ point. Run it ONLY when the settled fix touches control flow or behaviour — an
 off-by-one, a wrong operator/variable, a behaviour-changing config value, or a
 missing import that alters execution. In doubt → it is probably a `/bugfix`.

-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 For a logic fix: persist the STEP 1 located fix (root cause + the exact edit) to
 `.claude/tasks/plans/<date>-<slug>-<HHMM>.md`, then run
 `$HOME/.claude/lib/challenge-plan.md` with `PLAN` = that file, `KIND` =
@@ -135,10 +135,10 @@ mentioned: STOP and ask `"working tree dirty: stash and continue, or abort?"`.

 ## STEP 3 — DISPATCH EXECUTOR

-Dispatch the executor — sonnet by frontmatter pin, do not override:
+Dispatch the executor — sonnet by its row (frontmatter = off-state floor), do not override:

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="hotfixer")
 prompt: "CONTRACT: <path from STEP 1.7>
 LOCATED: <file(s) found in STEP 1 + the confirmed root cause>
@@ -236,7 +236,7 @@ Always append a 1-line entry to today's heading in `.claude/memory/journal.md` (

 **Language rule**: the journal line and any proposed BLK/LRN entries are ALWAYS written English AND caveman — fragments, articles dropped, code/IDs/quoted errors verbatim — per CLAUDE.md "Memory registries" (Always English, always caveman).

-`Skill(effort-low)` first (effort-shift: bookkeeping tail; send it in the same message as the memory-commit command).
+`mcp__model-router__route(phase="apply")` first (route: bookkeeping tail; send it with the memory-commit command).

 **Then commit the memory** — follow `$HOME/.claude/lib/capitalize-commit.md`: it
 surgically commits what capitalize just wrote (`.claude/memory` + `.claude/tasks`
@@ -14,7 +14,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## REQUEST
 $ARGUMENTS
@@ -181,12 +181,12 @@ This is the deterministic scaffold commit owner (closes BLK-010). The MVP is
 implemented on a `feature/*` branch off `develop` (STEP 8).

 ## STEP 6 — PLAN
-`Skill(effort-xhigh)` first, sent with the next tool call (effort-shift: turn reset; gate #1 ended the turn and the vendored `writing-plans` pin applies only when the user invokes it).
+`mcp__model-router__route(phase="plan")` first (route: resumed turn; gate #1 ended the turn).
 Invoke `writing-plans` (vendored superpowers skill) with BRIEF + skeleton.
 Granular tasks (2-5 min each), exact file paths, TDD: tests before code.

 ## STEP 6b — CHALLENGE THE PLAN (before the gate)
-`Skill(effort-xhigh)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="plan")` first (route: own level before the challenge; send it with the challenger dispatch).
 Before the human sees the implementation plan, harden it. Run
 `$HOME/.claude/lib/challenge-plan.md` with `PLAN` = the plan STEP 6 wrote under
 `docs/superpowers/plans/`, `KIND` = `build-plan`, `SCOPE` = the skeleton + task file
@@ -212,7 +212,7 @@ Approve and start? (yes / request changes)
 Changes → back to STEP 6. Approved → continue.

 ## STEP 8 — IMPLEMENT
-First: `Skill(effort-medium)` (effort-shift: dispatch span starts; send it in the same message as this step's first dispatch).
+First: `mcp__model-router__route(phase="orchestrate")` (route: dispatch span starts; send it with this step's first dispatch).
 Start the MVP feature branch off develop, then implement on it:
 ```bash
 bash "$HOME/.claude/lib/gitflow.sh" start feature mvp
@@ -224,7 +224,8 @@ Invoke `subagent-driven-development` (vendored superpowers skill) for the per-ta
 finishing-a-development-branch", stop and return.

 **Model routing (BDR-066):** every subagent dispatched under SDD — per-task
-implementers AND its reviewers — MUST carry `model: "sonnet"` in the Agent
+implementers AND its reviewers — MUST carry `model: "sonnet"` and
+`effort="medium"` (the `implement` level; a main route never reaches a child) in the Agent
 call. The plan is closed; execution and plan-conformity review are sonnet
 work. Reflection (task decomposition, review verdict arbitration) stays in
 this loop.
@@ -261,9 +262,8 @@ against the founding contract. Distinct axis from STEP 10 code review
 ([[LRN-095]]) — both run.

 ## STEP 10 — CODE REVIEW
-`Skill(effort-xhigh)` first, sent with the review dispatch (effort-shift: judgment dispatch; the reviewer is a built-in and inherits the level in force).
 Invoke `requesting-code-review` (vendored superpowers skill). **Model routing (BDR-077):** the
-review subagent it dispatches MUST carry `model: "opus"` in the Agent call —
+review subagent it dispatches MUST carry `model: "opus"` and `effort="xhigh"` in the Agent call —
 craft review is dispatched judgment, never inherited from the session. Fix
 all CRITICAL before proceeding.

@@ -316,7 +316,7 @@ articles dropped, code/IDs/quoted errors verbatim — per CLAUDE.md "Memory
 registries" (Always English, always caveman). The gate may mirror the user's
 language; entries must not.

-`Skill(effort-low)` first (effort-shift: bookkeeping tail; send it in the same message as the memory-commit command).
+`mcp__model-router__route(phase="apply")` first (route: bookkeeping tail; send it with the memory-commit command).

 **Then commit the memory** — follow `$HOME/.claude/lib/capitalize-commit.md`: it
 surgically commits the approved founding decisions (`.claude/memory` +
@@ -14,7 +14,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## REQUEST
 $ARGUMENTS
@@ -368,7 +368,7 @@ Lire le bloc `audit_stack:` du fichier `~/.claude/lib/project-archetypes/<archet
 | Entry | Action | Livraison |
 |---|---|---|
 | `analyze` | Déjà fait en STEP 5 | L3a |
-| `code-clean` | Spawn subagent `general-purpose` (audit-only, `model="opus"` — BDR-076: dispatched audits off the session model) | L3a |
+| `code-clean` | Spawn subagent `general-purpose` (audit-only, `model="opus"`, `effort="xhigh"` — BDR-076: dispatched audits off the session model) | L3a |
 | `cso` | Si gstack ON → Skill(cso). Sinon → Agent general-purpose avec checklist OWASP + deps audit | L3a |
 | `doc` | Spawn subagent `doc-syncer` (auto-mode OFF, report-only) | L3a |
 | `seo` | Subagents seo-analyzer + geo-analyzer en parallèle | L3b |
@@ -385,6 +385,7 @@ Lancer EN PARALLÈLE (un seul message, plusieurs Agent calls) les audits corresp
 Agent(
  subagent_type="general-purpose",
  model="opus",
+  effort="xhigh",
  description="Onboard — code-clean audit only (read-only, opus)",
  prompt="""
  AUDIT-ONLY mode — NO fixes, NO refactoring, NO file modifications.
@@ -422,6 +423,7 @@ bash $HOME/.claude/lib/toggle-external.sh list 2>/dev/null | grep -E "^gstack\s+
  Agent(
    subagent_type="general-purpose",
    model="opus",
+    effort="xhigh",
    description="Onboard — security audit fallback (archetype-adaptive)",
    prompt="""
    READ-ONLY security audit. No file modifications.
@@ -546,6 +548,7 @@ flux de dev sont deux formes distinctes ([[BDR-050]] pipeline dev ≠ audit).
 Agent(
  subagent_type="doc-syncer",
  model="opus",
+  effort="xhigh",
  description="Onboard — doc drift audit only",
  prompt="""
  MODE: audit — REPORT-ONLY, NO edits, NO auto-sync (no patch dispatch
@@ -666,6 +669,7 @@ Si le skill ne supporte pas `--output`, capturer la sortie et écrire à la main
 Agent(
  subagent_type="general-purpose",
  model="opus",
+  effort="xhigh",
  description="Onboard — static design review fallback",
  prompt="""
  AUDIT-ONLY mode — NO edits. Static design review du code UI.
@@ -710,6 +714,7 @@ Puis parser le JSON Lighthouse (scores perf/a11y/bp/seo/pwa + top opportunities)
 Agent(
  subagent_type="general-purpose",
  model="opus",
+  effort="xhigh",
  description="Onboard — static perf audit",
  prompt="""
  AUDIT-ONLY mode — NO edits.
@@ -753,6 +758,7 @@ Parser axe-core résultats (violations, incomplete, inapplicable, passes) → `.
 Agent(
  subagent_type="general-purpose",
  model="opus",
+  effort="xhigh",
  description="Onboard — static a11y audit",
  prompt="""
  AUDIT-ONLY mode — NO edits.
@@ -799,6 +805,7 @@ Spawn un subagent synthétiseur (isolé, chargé uniquement du contenu de `.onbo
 Agent(
  subagent_type="general-purpose",
  model="opus",
+  effort="xhigh",
  description="Onboard — synthèse vers .claude/audits/",
  prompt="""
  Lire tous les fichiers de <PROJECT_ROOT>/.onboard-audit/ :
@@ -892,7 +899,7 @@ Vérifier que les 4 fichiers `.claude/audits/ONBOARD_REPORT.md`, `.claude/audits
 ---

 ## STEP 7b — CHALLENGE THE PROPOSALS (before the human gate)
-`Skill(effort-xhigh)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="plan")` first (route: own level before the challenge; send it with the challenger dispatch).
 The 4 audit files are on disk; `AUDIT_PROPOSALS.md` is the artifact worth
 attacking before the human spends a gate on it. Run
 `$HOME/.claude/lib/challenge-plan.md` with `PLAN` =
@@ -30,7 +30,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 This skill orchestrates TWO specialist agents running in parallel, then
 merges their output into a single `.claude/audits/SEO.md` report. It is the main
@@ -325,7 +325,7 @@ templating.
 **PHASE A — collect (both domains, one message):**

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="seo-analyzer", model="sonnet")
 prompt: """
 MODE: collect
@@ -460,7 +460,7 @@ sentinel, emit the COLLECT REPORT, stop. No scoring, no bundle.
 ```

 **PHASE B — judge (both domains, one message, AFTER both COLLECT REPORTs
-are DONE):** no `model=` override — the opus frontmatter pins apply.
+are DONE):** no `model=` override — the opus rows apply (frontmatter = off-state floor).

 ```
 Agent(subagent_type="seo-analyzer")
@@ -510,7 +510,7 @@ the reports."
 ```

 ## STEP 1b — CHALLENGE THE FIX BUNDLE (advisory, before apply)
-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 Both envelopes now carry a `## FIX BUNDLE` — worth attacking before any edit lands.
 **Skip if intervention mode = conservative** (nothing is applied). Else persist both
 bundles (seo + geo, verbatim) to `.claude/tasks/plans/<date>-<slug>-<HHMM>.md`, then run
@@ -558,7 +558,7 @@ The two bundles may touch the same shared template (meta vs JSON-LD). Apply
 For each AUTO item, dispatch its `applier` at L1, passing the item verbatim:

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(subagent_type="hotfixer")     # or "feater" per the item's applier
 prompt: "<paste the bundle item: files, concern, current, expected,
  framework note + shared-file discipline>.
@@ -14,7 +14,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 ## REQUEST
 $ARGUMENTS
@@ -114,10 +114,10 @@ Inject ONLY what constrains: the NON-BINDING count does NOT enter the brainstorm
 (the injection inherits the OUTPUT filter — detail what binds, drop what doesn't).
 Consumption = INPUT INJECTION (we can't modify the external skill; we control its input).
 Refine request into validated design via Socratic questioning. Don't proceed until design approved.
-Turns after a user reply run at the session level until a tool call is paired with `Skill(effort-xhigh)` (effort-shift: turn reset).
+The first step of every turn after a user reply is `mcp__model-router__route(phase="plan")` (route: resumed turn).

 ## STEP 2 — PLAN
-`Skill(effort-xhigh)` first, sent with the next tool call (effort-shift: turn reset; brainstorm turns after a user reply run at the session level, and the vendored `brainstorming` pin applies only when the user invokes it).
+`mcp__model-router__route(phase="plan")` first (route: resumed turn after the brainstorm gate).
 Invoke `writing-plans` (vendored superpowers skill) with the validated design AND the 0d digest: every task
 must be consistent with the in-force constraints; where a task implements or affects one,
 note the ID inline. Break design into tasks (2-5 min each). Each task: exact file paths, full code, verification steps.
@@ -127,7 +127,7 @@ request nor the STEP 1 brainstorm settled (check the contract's CLARIFICATIONS
 first) → one batch before STEP 2b; answers append to the contract `[gated]`.

 ## STEP 2b — CHALLENGE THE PLAN (adversarial, before the gate)
-`Skill(effort-xhigh)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="plan")` first (route: own level before the challenge; send it with the challenger dispatch).
 Before the human sees the plan, harden it. Run `$HOME/.claude/lib/challenge-plan.md`:
 - `PLAN` = the plan STEP 2 wrote under `docs/superpowers/plans/`
 - `KIND` = `build-plan`
@@ -174,7 +174,7 @@ judges the diff against this ENRICHED contract, not the STEP 0e seed — so a
 criterion the design introduced is verified, not lost.

 ## STEP 4 — IMPLEMENT
-First: `Skill(effort-medium)` (effort-shift: dispatch span starts; send it in the same message as this step's first dispatch).
+First: `mcp__model-router__route(phase="orchestrate")` (route: dispatch span starts; send it with this step's first dispatch).
 Start the feature branch off develop, then implement on it:
 ```bash
 bash "$HOME/.claude/lib/gitflow.sh" start feature <name>
@@ -186,14 +186,15 @@ Invoke `subagent-driven-development` (vendored superpowers skill) for the per-ta
 finishing-a-development-branch", stop and return.

 **Model routing (BDR-066):** every subagent dispatched under SDD — per-task
-implementers AND its reviewers — MUST carry `model: "sonnet"` in the Agent
+implementers AND its reviewers — MUST carry `model: "sonnet"` and
+`effort="medium"` (the `implement` level; a main route never reaches a child) in the Agent
 call. The plan is closed; execution and plan-conformity review are sonnet
 work. Reflection (task decomposition, review verdict arbitration) stays in
 this loop.

 ## STEP 4b — ERROR RECOVERY (if STEP 4 fails)
 If a subagent returns a build error, failing test, or type error:
-1. `Skill(effort-max)` (effort-shift: error recovery; send it in the same message as the Read of the analyzer file below), then load
+1. `mcp__model-router__route(phase="escalate")` (route: error recovery; send it with the Read of the analyzer file below), then load
   `$HOME/.claude/agents/analyzer.md` in DEBUG MODE on the exact error output.
   Produce: root cause hypotheses (ordered), affected files, what NOT to touch.
 2. Present gate:
@@ -210,10 +211,10 @@ OPTIONS :
  C) Abort feature — preserve work done so far
 ```
 3. Wait for user choice. Do NOT auto-fix. Do NOT proceed without explicit approval.
-4. On resume the turn is at the session level (effort-shift: turn reset).
-   If A → `Skill(effort-medium)` sent with the re-dispatch, apply minimal fix, re-run STEP 4 for the failed task only. Max 2 retry attempts.
+4. On resume: `mcp__model-router__route(phase="plan")` first (route: resumed turn).
+   If A → `mcp__model-router__route(phase="orchestrate")` sent with the re-dispatch, apply minimal fix, re-run STEP 4 for the failed task only. Max 2 retry attempts.
   If still failing after 2 → fall back to options B or C.
-   If B or C → `Skill(effort-xhigh)` first, sent with the next tool call.
+   If B or C → continue at the plan level set above.
   If B → before skipping: scan remaining task list for tasks that depend on the failed task
     (look for references to the same file or function in subsequent tasks).
     If dependents found → present: "Tasks [N, M] depend on the skipped task.
@@ -243,9 +244,8 @@ conformity + security vs. craft/design) — both run, neither subsumes the
 other ([[LRN-095]]).

 ## STEP 6 — CODE REVIEW
-`Skill(effort-xhigh)` first, sent with the review dispatch (effort-shift: judgment dispatch; the reviewer is a built-in and inherits the level in force).
 Invoke `requesting-code-review` (vendored superpowers skill). **Model routing (BDR-077):** the
-review subagent it dispatches MUST carry `model: "opus"` in the Agent call —
+review subagent it dispatches MUST carry `model: "opus"` and `effort="xhigh"` in the Agent call —
 craft review is dispatched judgment, never inherited from the session. Fix
 all CRITICAL before proceeding.

@@ -277,7 +277,7 @@ Feature shipped implies at least one design decision worth capturing. Run this B

 If nothing substantive to log → print `CAPITALIZE: nothing substantive to log` and skip.

-`Skill(effort-low)` first (effort-shift: bookkeeping tail; send it in the same message as the memory-commit command).
+`mcp__model-router__route(phase="apply")` first (route: bookkeeping tail; send it with the memory-commit command).

 **Then commit the memory** — follow `$HOME/.claude/lib/capitalize-commit.md`: it
 surgically commits what capitalize just wrote (`.claude/memory` + `.claude/tasks`
@@ -30,7 +30,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 One pipeline per project: **security → clean → re-verify → reconcile →
 doc → convergence re-audit**, looping until a full pass applies zero new
@@ -169,8 +169,8 @@ honestly in the summary. Never loop past 3.

 ### Phase B — CLEAN

-1. Dispatch a read-only cleanup audit (analyzer — opus-pinned, BDR-076 —
-   or general-purpose with `model="opus"`; NOT the sonnet code-cleaner,
+1. Dispatch a read-only cleanup audit (analyzer — opus row, BDR-076 —
+   or general-purpose with `model="opus"`, `effort="xhigh"`; NOT the sonnet code-cleaner,
   which is now a fix executor): dead code, unused imports/exports,
   commented-out blocks, stale flags, norm violations. Findings as
   `id | file:line | finding | proposed fix`.
@@ -28,7 +28,7 @@ Run `$HOME/.claude/lib/model-gate.md`. Reflection here (planning, audit
 judgment, loop decisions) requires Fable/Opus. Verdict `small` → STOP: the
 gate prints the remedy; end the turn — no later step, no dispatch. Nominal
 (big) path is silent.
-EFFORT SHIFTS: follow `$HOME/.claude/lib/effort-shift.md` (BDR-107): medium when a dispatch span starts, own level before challenge synthesis, low at the bookkeeping tail, max at escalation; every shift goes in the same message as the step's first tool call, a lone Skill call is a no-op.
+ROUTING: follow $HOME/.claude/lib/effort-shift.md (phases via mcp__model-router__route).

 This skill orchestrates a narrow-scope standards audit :

@@ -180,7 +180,7 @@ Spawn a single `validator-analyzer` subagent with explicit scope and
 collected context :

 ```
-Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
 Agent(
  subagent_type="validator-analyzer",
  description="validate — W3C HTML + CSS + WCAG audit",
@@ -255,7 +255,7 @@ grep -c '^### \[Critique\]' .claude/audits/VALIDATE.md
 ---

 ## STEP 2b — CHALLENGE THE FIX BUNDLE (MODE=fix only, advisory)
-`Skill(effort-high)` first (effort-shift: own level before the challenge; send it in the same message as the challenger dispatch).
+`mcp__model-router__route(phase="reflect")` first (route: own level before the challenge; send it with the challenger dispatch).
 Skip if MODE=audit (no bundle exists). Else, before the STEP 3 gate, harden the bundle:
 extract the `## 5. Fix bundle` section from VALIDATE.md to
 `.claude/tasks/plans/<date>-<slug>-<HHMM>.md` (a clean, blind-judgeable artifact), then run
@@ -313,7 +313,7 @@ Options :
   share files:

   ```
-   Skill(effort-medium)   # effort-shift: dispatch span starts; send with the Agent call below in ONE message
+   mcp__model-router__route(phase="orchestrate")   # route: dispatch span starts; send with the Agent call below in ONE message
   Agent(subagent_type="hotfixer")
   prompt: "<paste the file-group's bundle items: file, issue, current,
     expected fix>.