Owner-ratified 2026-07-20: architect, grounding-check, tdd-author and
debugger pin fable/xhigh — cycle-reach singleton gates whose miss
silently ratifies or poisons an entire cycle (drift verdict, autonomous
sign-off signature, RED executable-spec, root-cause). The set is
closed: extending it requires fresh owner ratification, no fable agent
ever runs per-task in a loop or in a parallel fan-out, and workflow
scripts stay fable-free (the implement-loop quality gate caps at opus).
Policy home: docs/agent-template.md $ model rule 1 (effort: fable
gates stay xhigh, not max); the workflow policy headers now point at
the exception instead of the former blanket ban.
Effort joins model as a mandatory pin: an omitted field inherits the
session effort, coupling every dispatch's thinking budget to whatever
the user happens to be chatting at (often xhigh) — the same
session-state coupling the model pin removes. The assignment follows
the model split:
- xhigh on every opus agent (judgement roles are the pipeline's
quality floor and must not degrade with the session);
- high on every sonnet agent (tightly-scoped plan execution gains
little from xhigh but pays its latency per dispatch, and these are
the per-task in-loop roles — wall-clock is the efficiency metric;
not lower than high, since re-loops cost more than saved thinking);
- medium inline in the workflow scripts for schema-bound
extraction/verification stages that author no code (preflight,
plan-extract, mini-verify, tree-check, finalize, build/suite
verify).
Workflow agent() calls pass effort explicitly on every call — whether
frontmatter effort propagates through an agentType dispatch is
undocumented, so the scripts do not rely on it. Policy documented in
docs/agent-template.md § effort, mirroring § model.
Agents and workflows previously carried no model field, so every
dispatch inherited the session model — including fable, which is
banned for all plugin agents and workflows by owner decree. Every
dispatch now pins opus or sonnet explicitly.
- opus (low-volume judgment gates whose misses silently poison
downstream work): architect, bencher, debugger, fieldtester,
grounding-check, plan-recon, quality-reviewer, spec-skeptic,
tdd-author
- sonnet (mechanical scope, in-loop or fanned out): docwriter,
glossary-extractor, implementer, spec-reviewer, synthetic-user,
tester
- workflows: all 13 agent() call sites pin a model — sonnet
everywhere except the quality-reviewer gate in implement-loop,
the loop's last correctness check (spec-reviewer only gates
task-text correspondence; real-bug finding is the documented
opus strength)
- docs/agent-template.md: model is now a mandatory frontmatter
field, with the assignment rule and the fable ban recorded
The profile was never parsed — it was prose the skill bodies told the model to read, so most slots were dead, constant across every project, or fiction (the whole pipeline block, including the "tdd is opt-in" claim, was enforced by nothing).
Split it in two: constants become fixed conventions named directly by the skills (new docs/conventions.md), and the few genuinely per-project facts move to each project's CLAUDE.md under '## Skills plugin: project facts'. tdd/fieldtest/docwriter are now always available; the only behavioural toggle left is spec auto-sign.
Delete docs/profile-schema.md and templates/project-profile.yml; add docs/conventions.md and a project-facts section to templates/CLAUDE.md.fragment; rewrite all SKILL/agent prose and the pipeline/design/migration/README/INSTALL docs accordingly.
The carrier (symptom/repro_known/recent_iter) and handoff
(red_test_path/cause_summary/constraint) field definitions were
tabled in full in both SKILL.md and debugger.md — the exact
duplication that let the `constraint` wording drift earlier.
Since the debugger agent runs in a fresh context, it must carry
both contracts inline regardless; that makes debugger.md the
natural single source. Mark its Carrier-contract and Output-format
tables authoritative, fold in the richer field descriptions that
only SKILL.md had, and reduce SKILL.md to naming the fields plus a
pointer — no field semantics restated. Drift-prone prose now lives
in exactly one place. Consistent with SKILL.md's own stated split
(debugger.md = source of truth; skill = trigger/dispatch/handoff).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase 3 previously said only "smallest possible reproducer" — a
passive property an agent can satisfy by name while still asserting
against the full reproducing fixture. Sharpen it into an explicit
two-step discipline: minimize the trigger (delta-reduce until one
more cut makes the symptom vanish) and make the fixture autonomous
(inline input, no shared fixtures/DB seeds/clocks/server boots
unless the bug is genuinely at that integration boundary).
- Iron Law gains: an un-minimized repro is not a RED test
- Phase 3 rewritten with explicit Minimize + Autonomous steps
- 3 rationalization rows + 4 red flags for the "full fixture
reproduces deterministically, ship it" failure mode
- SKILL.md overview/handoff mirrored at orchestrator altitude
Baseline (writing-skills RED-first): 6 subagent runs showed the old
wording usually steered right but relied on agent instinct; GREEN:
2 runs under the targeted full-fixture pressure now reduce to the
minimal trigger and cite the contract verbatim.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Second skill migrated using the boss pattern. Purely a discipline
skill (RED-first bug fixing); no AILang-specific contracts.
Vocabulary substitutions:
- AILang → "this project" / "the project"
- "ailang-debugger" / "ailang-bencher" / "ailang-architect"
→ "debugger" / "bencher" / "architect" (ailang- prefix dropped)
- "Boss" → "orchestrator"
AILang-specific bits replaced with profile slots:
- `cargo build` / `cargo test` → `commands.build` / `commands.test`
- `ail emit-ir`, `ail run`, `ail build` → "the project's run command"
(generic — these were AILang CLI specifics)
- `crates/ail/tests/e2e.rs` hardcoded test path → "the testing
location idiomatic for this project"
- `design/INDEX.md` → `paths.design_ledger` (optional; if the
project does not have one configured, that step short-circuits)
Universal substance preserved verbatim:
- Iron Law (3 lines)
- Four phases + Phase 4.5 (the three-failures-means-architecture
rule)
- Status protocol (DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT /
BLOCKED)
- All 7 Common Rationalisations rows
- All 8 Red Flags bullets
Dropped from original:
- "former CLAUDE.md 'Bug fixes — TDD, always' section before the
2026-05-09 skill-system migration" — AILang history, not
load-bearing for the discipline
- "for the AILang project at /home/brummel/dev/ailang" — AILang
identity, replaced with generic "this project"
Cross-refs (post-flatten):
- `../implement/SKILL.md` for the GREEN handoff target
- `agents/debugger.md` from the skill body
claude
Brummel