Fourth skill via the boss pattern. audit is the cycle-close
cleanup gate; architect does read-only drift review against
the design ledger; bencher does hypothesis-driven performance
diagnostics.
Profile gains one slot:
- `commands.architect_sweeps` — optional list of project-
specific architect sweep commands. The architect agent runs
these in addition to its universal checks; non-zero exit =
drift suspicions. AILang uses this for the
bench/architect_sweeps.sh design-honesty / history-anchor
/ lockstep-invariant detector.
The existing `commands.regression` slot now does double duty:
the audit skill walks it in Step 2; the bencher agent reads
the failing script for diagnostics.
Vocabulary substitutions:
- AILang → "this project"
- milestone → cycle
- Boss → orchestrator
- ailang-architect, ailang-bencher → architect, bencher
AILang-specific bits replaced or removed:
- `bench/check.py && bench/compile_check.py && bench/cross_lang.py`
→ `commands.regression` list
- `bench/architect_sweeps.sh` → `commands.architect_sweeps`
- design/INDEX.md / design/contracts/ / design/models/
→ `paths.design_ledger` / `paths.design_contracts` /
`paths.design_models`
- `bench/run.sh`, `bench/orchestrator-stats/`, `runtime/rc.c`,
`runtime/bump.c` (in bencher) → generic harness / production-
path references
- RC + uniqueness + bump + implicit-mode/explicit-mode
framework (the entire AILang allocator-comparison
calibration) → generic "cost-paying variant vs control"
framing; the hypothesis examples generalised to abstract
perf claims
- The two specific lockstep invariants in architect
(Pattern::Lit::* ↔ pre_desugar_validation; lower_app ↔
is_static_callee) → "the project's CLAUDE.md enumerates
the known pairings; walk each one against the cycle diff"
(the concrete pairings stay AILang-only, in AILang's
CLAUDE.md, not in the plugin)
- The Floats fieldtest "B1 canonical example" reference →
dropped (AILang-specific anchor)
- `design/contracts/0007-honesty-rule.md` cross-ref → dropped
(AILang-specific contract); the honesty principle survives
in the architect's commit-body-truthfulness check
Universal substance preserved verbatim:
- All three Iron Law clauses for audit, architect, bencher
- audit's four-step process; architect's eight-step process;
bencher's hypothesis-first methodology + fixture-pairing
rule + honesty rules
- audit + architect + bencher exit code 0/1/2 semantics
- All Common Rationalisations (5/6/8) and all Red Flags
(5/6/7) rows across the three files, vocabulary-substituted
- bencher's "tie is not a result" doctrine intact
Bencher is the most language-coupled of the seven (was
AILang-allocator-specific). Generalised to a performance-
benchmarker; the discipline (hypothesis-first, design-against
not around, ties-are-bench-info) survives intact. AILang's
RC+bump examples kept in spirit via the generic "cost-paying
vs control" framing.
~/dev/skills/skills/boss/ was visually awkward (skills/skills
read twice) and structurally unnecessary — the skills ARE the
repo's main content, not a sub-collection inside it.
Layout changes:
- boss/SKILL.md moves to the repo root
- skills/README.md (migration notes) moves to docs/migration.md
where documentation-about-the-system belongs
- install.sh discovers skills via the SKILL.md marker file
instead of a hardcoded skills/<name>/ path, so future skill
additions just drop in at the root
Cross-references in boss/SKILL.md (../README.md, ../brainstorm,
etc.) now resolve against the repo root instead of the old
skills/ subdir, which is what they describe: top-level
README is the skill table; sibling skill dirs are the other
migrated skills.
First skill migrated from AILang's in-tree skills/. boss carries
the autonomous orchestrator authority (god-mode: dispatches every
other skill, decides done-state vs bounce-back), so it is the
load-bearing pilot for the migration pattern.
Profile schema gains three slots that boss needs:
- `git.issue_tracker.url` — browsable issue list URL
- `git.issue_tracker.list_cmd` — shell command listing open issues
- `notifications.command` — script invoked on done-state /
bounce-back; falls back to chat if empty
AILang-specific bits dropped from the prose:
- AILang/Gitea URL + tea CLI hardcoding → profile slots
- `design/contracts/0004-feature-acceptance.md` cross-reference
→ project CLAUDE.md (not the plugin's concern)
- "Boss" terminology → "orchestrator" (the plugin term; "Boss"
was AILang vocabulary)
- "Brummel-as-LLM" → "the orchestrator"
- "milestone" → "cycle" (the profile's vocabulary slot)
Universal substance preserved verbatim: Iron Law, the five
process steps, the four bounce-back triggers + new-cycle
rationale, notification protocol, done-state editorial rules,
Common Rationalisations, Red Flags. No discipline-prose compression.
design/out-of-scope claim retracted: boss DOES generalise, and
its body now demonstrates how — the queue mechanic is a single
shell-command slot, not a transport-coupled contract.
skills/README.md flags boss as the landed pilot; the other seven
skills follow once the pattern is approved.
Establishes the repository structure for the skills plugin:
- README + INSTALL describing the two-layer split (plugin
mechanics vs per-project profile)
- docs/design, profile-schema, pipeline, agent-template covering
the universal discipline constants and the profile slot model
- templates/project-profile.yml as a copy-and-fill starting point
- templates/CLAUDE.md.fragment with the baseline orchestrator
rules a project can import
- install.sh / uninstall.sh wiring skills/ + agents/ into
~/.claude/ via idempotent symlinks
- skills/ and agents/ directories empty except for migration
READMEs; the actual SKILL bodies and agent files migrate
from ~/dev/ailang/skills/ in the next iteration.
No skill or agent runs yet — this commit only stands up the
structure and documents the substitution model.
Brummel