After the report the skill proposes fixes (plan phase), stops for the
user's acceptance, applies accepted ones via bugfixer and the
verify-secure gates, then re-scans. scan.py gains --assert-absent
(contract oracle, positive control) and --baseline (no new hit).
probe.py observes a running target the user owns and names, driven by a
plan built from the static findings. Five probes: anon-read, cross-user,
no-auth route, CORS reflection, capped rate-limit burst. GET/HEAD/OPTIONS
only, --authorized gate, secrets from the environment, same-host redirect
only, bounded request budget. SKILL STEP 5, checks.md reference, docs.
Suite guardrails-probe.test.sh (16 checks) against a localhost fixture.
Kill switch fails closed: a present-but-unreadable override at first load
or a non-boolean enabled turns the router off (logged); /route reload says
when the previous config was kept. Prompt rules with nested quantifiers
are dropped; a config path that is not a regular file reads as failed;
caught errors log kind + code only (errWord); rejected keys are masked in
logs (keyWord), alias keys match KEY_NAME, prototype names are never keys;
offers capped at 256; a models alias without a fallback list is ranked at
the end of the default chain; canonical matches a table id at a '-'
boundary only; logCall/noteMain cannot unroute a step; route-tool failure
text no longer claims nothing was routed.
Repo side: mods suite probes the 'claude plugin test' usage line, doctor
bounds plugin list to 60 s, update-all skips @skills-dir mods.
Kit 431/431, full make test green.
The text regex becomes a prefilter. The command is split into simple
commands by an awk tokenizer (quotes, escapes, ; && || | ( ) backticks,
heredoc bodies dropped) and a push is only a simple command whose argv[0]
is git (or */git) with push or send-pack as its first non-option word.
grep "git push", git log -S, git config --get push.default, git stash
push, heredocs and commit messages quoting a push are no longer denied.
bash|sh|zsh -c scripts are re-checked (depth 3); wrappers (sudo, env,
eval, xargs, timeout, git subtree...), assignments whose value reads as
a push, a missing awk or > 2000 simple commands keep the text verdict.
Prefilter also matches "git" push (quote characters stripped).
Suite 98 -> 124 checks.
Plain composer prompts with no route in force get a turn-scoped effort
from $.model.classify (design/analysis/coding/bookkeeping/chat → phase
effort, effort only, never the model). Bounded by a 3 s clock race, a
user interrupt neither counts nor writes, three failures in a row pause
it for cooldownMinutes (one toast, status marker, cleared by /route
reload). No dialog, no routing.json write on a classified route. New
Config key `classify` (default on, pickSwitch), `/route classify on|off`
session toggle, `/route show` line and argumentHint. An explicit user
/effort beats the guess (engineBase check).
Docs: README classifier paragraph, USAGE row + sentence, CHANGELOG,
effort-shift.md. Kit suite 428 tests.
verbose now logs one line per real change, built from the decision
itself: main 'fable/high → fable/xhigh (plan: skill /ship-feature)' once
per turn per transition, a hand-off line per agent dispatch deduped per
(type, target) 'main fable/high → agent verifier sonnet/xhigh (row verify,
row)', a later agent effort move, and an answered-by anomaly for agents.
The four stream lines (step, answered by, spawn, route JSON, skill path)
are gone; the host prefixes the plugin name, so the new lines carry none.
Lines are built inside safely before next (a log failure never unroutes a
step); names are cleaned (≤ 40 code points). Residuals: failure texts go to
the log with a generic answer (forget, ask), file fragments cleaned at
render, floorFile name allowlisted, __proto__ refused in restoreOf, the
changed scan limited to rows, dialog Change offers only shipped phases,
a post-answer write failure keeps the key asked. Kit suite 284 → 358.
Contract .claude/tasks/contracts/2026-10-11-model-router-w4a-logs-residuals-1637.md,
plan r3: 3 lenses (BLOCKER: agent model moves are decided at spawn) + 1
confirmation, feater + 4 rounds, GATE 0 MET, verifier at the cap on
coverage (user-accepted), security PASS + 2 MEDIUM fixed.
Clears first-use decisions from the tracked routing.json through the
existing writer: a name is forgotten in every table (confirmed, changed
with the row restored to its recorded shipped phase under guards, project
exceptions pruned) and asked again; all and projects ask a confirmation in
the engine dialog (Cancel first) and hold the single-dialog slot; nothing
is written when there is nothing to forget; the answer names what was
restored and the frontmatter floor to realign when one was aligned; the
route tool has no forget path. Docs name the new writer. Kit suite 232 → 284.
Contract .claude/tasks/contracts/2026-10-11-model-router-w3c-forget-1457.md,
plan r3: 3 lenses + 1 confirmation, feater + 3 rounds (one real defect),
GATE 0 MET, verifier at the cap on coverage (user-accepted), security PASS.
The literal deny patterns miss spellings such as `npm i <pkg> -g`.
The classifier entry covers every form and asks for a vetting summary
(publisher, age, downloads, install scripts, advisories) first.
INT/TERM trap removes the mktemp sibling and exits 130 (traps restored,
never EXIT); re-read message honest and reached by a stubbed test; rejected
map line printed through printf %q; suite guards mktemp -d and skips the
read-only case under root. Cases T13b, T15, T15b, T16.
- lib/effort-pins.txt (map) + lib/effort-pins.sh (idempotent re-apply)
replace the hardcoded brainstorming/writing-plans loop; called after the
last vendoring step of install-plugins.sh AND update-all.sh (the resync
dropped the pins until the next make plugin)
- design stack high uniform (last loaded wins), superpowers, agent-skills,
21st pack pinned from the map; skills-perso low, pdf-translate medium,
site-motion high
- doctrine: design stack loads paired with the first Read; one level per
stack (CLAUDE.global.md, lib/effort-shift.md)
- lib/effort-audit.py prints thinking coverage per scope (sub-agent records
carry no thinking count on ~94 % of requests)
- census map-driven + fixture suite lib/tests/effort-pins.test.sh; docs
README/USAGE/CHANGELOG; contract + TODO plan
Ubuntu's gitleaks 8.16 package has no git subcommand, so the hook's
"unknown command" exit 1 blocked every commit as a leak. Probe
gitleaks git --help once, fall back to protect --staged; regenerate the
installed hooks. T16c simulates a missing binary with a /usr/bin symlink
farm minus gitleaks instead of a shorter PATH.
Every superpowers-prefixed skill call in ship-feature, init-project, tour,
deploy, audit-delta, plugin-advisor and lib/analyze-before-plan now names
the vendored skill directly. finishing-a-development-branch is described
as the upstream skill this config does not vendor (gitflow finish is the
integration path). CLAUDE.global.md Skill routing maps the four
non-vendored skills the vendored text still references. settings.json
loses the plugin key and its marketplace block; README, USAGE,
plugin-advisor and the profile skill describe superpowers as vendored
skills, always on, zero plugin cost. CHANGELOG entry with a known
residual.
The design gate checked the 21st CLI with command -v only, so an
installed-but-signed-out CLI read as READY and every 21st step failed
downstream. tool_active now probes 21st whoami through a three-state
function: signed in (TWENTYFIRST_TOKEN or API_KEY_21ST set, or 'Logged in
as'), signed out (exact 'Not logged in'), unknown (rc != 0, timeout,
unexpected output). Signed out is a new verdict, SIGN-IN REQUIRED, exit
12: design-gate.md tells the orchestrator to ask the user to run
! 21st login, end the turn, re-run the gate on their reply, and to skip
21st only on an explicit 'proceed without 21st', never silently. Unknown
surfaces as exit 11 with the whoami diagnostic and a CLI-runtime remedy,
so a node/PATH failure can never loop on a sign-in prompt. INCOMPLETE
still wins. Hermetic suite lib/tests/design-tool-gate.test.sh (stub CLI,
fixture repo through DESIGN_GATE_REPO_OVERRIDE) covers every state.
settings.json: ENABLE_STOP_REVIEW=0 (the plugin's own switch: no more
Opus call on every turn that changes code, 0 findings in 6 days, 1
recorded false positive; the regex layer and the commit/push agentic
review stay on), brightdata-plugin@synced false (keyless-useless, its MCP
skill would hijack WebFetch/WebSearch), frontend-design official plugin
entry gone (uninstalled: byte-identical to the managed copy).
CLAUDE.global.md routes Ship/PR to ship-feature (gstack ship takes
origin/HEAD = main as base), drops ship/context-save from the gstack-off
list and 21st-ui-review from the design review line (trio is max-only).
deploy's table no longer points at land-and-deploy/setup-deploy.
plugin-advisor.md describes security-guidance's real mechanics. CHANGELOG
Unreleased entry with a Known residual section.
Two security-gate LOW notes closed on user ask: the SAFE guard uses
re.fullmatch so a trailing newline is rejected; commit (40 hex), source
(github.com owner/repo) and path (SAFE class, no traversal) are validated
before any URL is built, INVALID marker names the field. Suite 12 cases.