feat(routing): skill-runner pins move from fable to opus

Fable is the advisor (BDR-150): the client-handover skill-runner children and the model-gate dispatch doctrine pin opus. A pinned child's route answer "fixed at spawn" passes the gate; a repo-wide census refuses any fable pin.
This commit is contained in:
bchanot committed 2026-11-16 23:55:31 +01:00
1 parent d12c2b045c
commit beebfe2d82
5 files changed
+25 -20

No files matched your search

+7 -7
View File
@@ -267,10 +267,10 @@ the gate.
**Model routing (BDR-077):** EVERY `general-purpose` skill-runner dispatch in **Model routing (BDR-077):** EVERY `general-purpose` skill-runner dispatch in
this pipeline (initial audits, fix-loop re-dispatches, commit-change, this pipeline (initial audits, fix-loop re-dispatches, commit-change,
web-validate) carries `model: "fable"` and `effort="high"` — the child hosts gated web-validate) carries `model: "opus"` and `effort="high"` — the child hosts gated
orchestration on the pipeline's behalf; it must never inherit the session model. orchestration on the pipeline's behalf; it must never inherit the session model.
For web projects, dispatch in **a single message with two parallel Agent calls** (each with `model: "fable"`, `effort="high"`): For web projects, dispatch in **a single message with two parallel Agent calls** (each with `model: "opus"`, `effort="high"`):
| Audit (web) | Subagent | Prompt template | | Audit (web) | Subagent | Prompt template |
|---------------|-------------------|-----------------| |---------------|-------------------|-----------------|
@@ -429,7 +429,7 @@ for CSO) in the format
### Re-dispatch prompt template (SEO + GEO loop) ### Re-dispatch prompt template (SEO + GEO loop)
Send to `general-purpose` subagent (`model: "fable"`, `effort="high"`): Send to `general-purpose` subagent (`model: "opus"`, `effort="high"`):
> Read `~/.claude/skills/pack-seo/skills/seo/SKILL.md` and re-run it on this project in > Read `~/.claude/skills/pack-seo/skills/seo/SKILL.md` and re-run it on this project in
> **conservative (audit-only) intervention mode**: re-score and leave both > **conservative (audit-only) intervention mode**: re-score and leave both
@@ -460,7 +460,7 @@ Send to `general-purpose` subagent (`model: "fable"`, `effort="high"`):
### Re-dispatch prompt template (HARDEN loop) ### Re-dispatch prompt template (HARDEN loop)
Send to `general-purpose` subagent (`model: "fable"`, `effort="high"`): Send to `general-purpose` subagent (`model: "opus"`, `effort="high"`):
> Read `~/.claude/skills/harden/SKILL.md` and re-run it with `--fix` ONLY > Read `~/.claude/skills/harden/SKILL.md` and re-run it with `--fix` ONLY
> up to the bundle: stop at `READY TO APPLY — awaiting dispatcher > up to the bundle: stop at `READY TO APPLY — awaiting dispatcher
@@ -473,7 +473,7 @@ Send to `general-purpose` subagent (`model: "fable"`, `effort="high"`):
### Re-dispatch prompt template (CSO loop — non-web only) ### Re-dispatch prompt template (CSO loop — non-web only)
Send to `general-purpose` subagent (`model: "fable"`, `effort="high"`): Send to `general-purpose` subagent (`model: "opus"`, `effort="high"`):
> Read `~/.claude/skills/pack-gstack-dev/skills/cso/SKILL.md` and re-run it in **daily mode**. > Read `~/.claude/skills/pack-gstack-dev/skills/cso/SKILL.md` and re-run it in **daily mode**.
> Previous score: **`<SCORE_CSO_PREVIOUS>`/20** — below threshold. > Previous score: **`<SCORE_CSO_PREVIOUS>`/20** — below threshold.
@@ -562,7 +562,7 @@ listed changes by hand before deploy." Continue to STEP 6.
If `PENDING_CHANGES` non-empty → invoke /commit-change skill via subagent: If `PENDING_CHANGES` non-empty → invoke /commit-change skill via subagent:
> Dispatch `general-purpose` subagent (`model: "fable"`, `effort="high"`). Prompt: > Dispatch `general-purpose` subagent (`model: "opus"`, `effort="high"`). Prompt:
> >
> "Read `~/.claude/skills/commit-change/SKILL.md` and execute. All pending > "Read `~/.claude/skills/commit-change/SKILL.md` and execute. All pending
> changes were produced by the client-handover ship pipeline during the > changes were produced by the client-handover ship pipeline during the
@@ -682,7 +682,7 @@ Skip if `VALIDATE_SKIPPED=true` or `PROJECT_TYPE != web` (in either case
ensure `VALIDATE_SKIPPED=true` is set so the gate logic in STEP 8 treats ensure `VALIDATE_SKIPPED=true` is set so the gate logic in STEP 8 treats
VALIDATE as not-applicable rather than failed). VALIDATE as not-applicable rather than failed).
Dispatch `general-purpose` subagent (`model: "fable"`, `effort="high"`): Dispatch `general-purpose` subagent (`model: "opus"`, `effort="high"`):
> Read `~/.claude/skills/pack-web-validate/skills/web-validate/SKILL.md` and execute against the > Read `~/.claude/skills/pack-web-validate/skills/web-validate/SKILL.md` and execute against the
> deployed URL: `<DEPLOYED_URL>`. Audit W3C HTML validity (validator.nu), > deployed URL: `<DEPLOYED_URL>`. Audit W3C HTML validity (validator.nu),
+5 -4
View File
@@ -12,6 +12,7 @@ call. The answer names the id main runs on next.
| answer | action | | answer | action |
|---|---| |---|---|
| names a fable or opus id | proceed, SILENT | | names a fable or opus id | proceed, SILENT |
| says the model is `fixed at spawn` (sub-agent) | proceed, SILENT |
| names sonnet, haiku, anything else; "is off"; tool absent | **STOP** | | names sonnet, haiku, anything else; "is off"; tool absent | **STOP** |
**STOP means**: print exactly `⛔ MODEL GATE — session on <model>. **STOP means**: print exactly `⛔ MODEL GATE — session on <model>.
@@ -24,7 +25,7 @@ the turn. No later step runs, no agent is dispatched, nothing is edited.
The gate guards the MAIN loop only. Typed agents are routed by their The gate guards the MAIN loop only. Typed agents are routed by their
model-router row (`model:` frontmatter = off-state floor). Built-ins model-router row (`model:` frontmatter = off-state floor). Built-ins
(general-purpose / Explore / Plan) carry an explicit `model=` at every call (general-purpose / Explore / Plan) carry an explicit `model=` at every call
site: `model: "fable"` when the child reflects/orchestrates for the main site, its tier: `model: "opus"` = skill-runners (the child reflects or
loop (skill-runners), else its tier (opus = dispatched judgment, sonnet = orchestrates for the main loop) and dispatched judgment, sonnet = execution,
execution, haiku = mechanical probes). A built-in judgment dispatch also haiku = mechanical probes; never fable (BDR-150, the advisor). A built-in
carries an explicit `effort=` (`lib/effort-shift.md`). judgment dispatch also carries an explicit `effort=` (`lib/effort-shift.md`).
+4 -2
View File
@@ -221,8 +221,10 @@ n_opus="$(grep -c 'model="opus",$' "$R/skills/onboard/SKILL.md")"
n_eff="$(grep -c 'effort="xhigh",$' "$R/skills/onboard/SKILL.md")" n_eff="$(grep -c 'effort="xhigh",$' "$R/skills/onboard/SKILL.md")"
[ "$n_opus" -ge 7 ] && [ "$n_opus" -eq "$n_eff" ] && ok \ [ "$n_opus" -ge 7 ] && [ "$n_opus" -eq "$n_eff" ] && ok \
|| ko "onboard: $n_opus model=\"opus\" dispatches vs $n_eff effort=\"xhigh\"" || ko "onboard: $n_opus model=\"opus\" dispatches vs $n_eff effort=\"xhigh\""
bad="$(grep 'model: "fable"' "$R/agents/client-handover-writer.md" | grep -vc 'effort="high"')" n_opus="$(grep -c 'model: "opus"' "$R/agents/client-handover-writer.md")"
[ "$bad" -eq 0 ] && ok || ko "client-handover-writer: $bad model: \"fable\" line(s) without effort=\"high\"" n_eff="$(grep 'model: "opus"' "$R/agents/client-handover-writer.md" | grep -c 'effort="high"')"
[ "$n_opus" -eq 7 ] && [ "$n_opus" -eq "$n_eff" ] && ok \
|| ko "client-handover-writer: $n_opus model: \"opus\" lines vs $n_eff with effort=\"high\" (want 7/7)"
for s in ship-feature init-project feat bugfix web-validate seo hotfix geo harden code-clean audit-delta tour onboard; do for s in ship-feature init-project feat bugfix web-validate seo hotfix geo harden code-clean audit-delta tour onboard; do
has "$(skdir "$s")/SKILL.md" 'ROUTING: follow $HOME/.claude/lib/effort-shift.md' has "$(skdir "$s")/SKILL.md" 'ROUTING: follow $HOME/.claude/lib/effort-shift.md'
done done
+8 -6
View File
@@ -85,14 +85,16 @@ lacks "skills/tour/SKILL.md" 'description="tour runner", model='
has "skills/onboard/SKILL.md" 'model="opus"' has "skills/onboard/SKILL.md" 'model="opus"'
has "skills/tour/SKILL.md" 'model="opus"' has "skills/tour/SKILL.md" 'model="opus"'
has "lib/challenge-plan.md" 'BDR-076' has "lib/challenge-plan.md" 'BDR-076'
# 12) BDR-077 W1 — no-inherit: skill-runner children pinned fable at every # 12) BDR-077 W1 — no-inherit: skill-runner children pinned opus since
# call site; code-review dispatches carry opus; doctrine in model-gate. # BDR-150 (Fable is the advisor, never a dispatch target); code-review
# (fable dispatch alias spike-verified 2026-07-19: resolves # dispatches carry opus; doctrine in model-gate.
# claude-fable-5, enum-validated, loud failure — never silent fallback) has "agents/client-handover-writer.md" 'model: "opus"'
has "agents/client-handover-writer.md" 'model: "fable"'
has "skills/ship-feature/SKILL.md" 'model: "opus"' has "skills/ship-feature/SKILL.md" 'model: "opus"'
has "skills/init-project/SKILL.md" 'model: "opus"' has "skills/init-project/SKILL.md" 'model: "opus"'
has "lib/model-gate.md" 'model: "fable"' has "lib/model-gate.md" 'model: "opus"'
has "lib/model-gate.md" 'fixed at spawn'
hits="$(git -C "$R" grep -nE 'model ?[:=] ?"fable"' -- agents skills lib ':!lib/tests')"
[ -z "$hits" ] && ok || ko "fable dispatch pin left: $hits"
lacks "lib/model-gate.md" 'model: "sonnet" in the Agent call' lacks "lib/model-gate.md" 'model: "sonnet" in the Agent call'
# 13) BDR-077 W2 — plugin split: probe (sonnet, facts only) + advisor # 13) BDR-077 W2 — plugin split: probe (sonnet, facts only) + advisor
# reasoner (opus, PROBE REPORT is ground truth, fail-closed); gate # reasoner (opus, PROBE REPORT is ground truth, fail-closed); gate
+1 -1
View File
@@ -31,7 +31,7 @@ Load and follow strictly:
Execute the CLIENT HANDOVER WRITER agent on this project. It runs the Execute the CLIENT HANDOVER WRITER agent on this project. It runs the
audit/fix/gate pipeline INLINE on the big session model (gated above), its audit/fix/gate pipeline INLINE on the big session model (gated above), its
skill-runner children dispatched `model: "fable"`, then delegates the skill-runner children dispatched `model: "opus"`, then delegates the
client deliverable to the two-mode `handover-doc-writer` subagent — client deliverable to the two-mode `handover-doc-writer` subagent —
synthesize on opus, render (Markdown + branded HTML + PDF) on the sonnet synthesize on opus, render (Markdown + branded HTML + PDF) on the sonnet
pin (BDR-077). pin (BDR-077).