edbbb68f972f69cb34152c7258d094e3cbe94b7f
108 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
808044c0cf |
fieldtest: skill + fieldtester agent migrated
Fifth skill via the boss pattern. fieldtest empirically tests whether a shipped cycle is usable by a downstream consumer who has only the public interface. Profile gains two slots: - `paths.public_interface` — list of dirs/files the fieldtester may read (the project's outward-facing surface: README, design ledger, docs, examples) - `paths.fieldtest_examples` — where the fieldtester writes its fixtures The forbidden zone is derived: everything not in `paths.public_interface` (especially `paths.code_roots` and `paths.bench_dir`) is closed to the fieldtester. This is the load-bearing source-isolation discipline. Vocabulary substitutions: - AILang → "this project" - milestone → cycle - Boss → orchestrator - ailang-fieldtester → fieldtester - "AIL Surface form / .ail" → "the project's canonical authoring or consumer form" - "design/INDEX.md + design/models/" → `paths.public_interface` - "crates/, runtime/, bench/" → `paths.code_roots`, `paths.bench_dir` AILang-specific bits dropped: - The form-a-default-authoring milestone history (2026-05-13) and the eight `.ail.json` carve-outs — AILang-specific schema-migration detail; the universal rule is just "canonical authoring form only" - The ail check / ail build / ail emit-ir CLI commands — the fieldtester now uses "the project's user-facing entry point" - Per-iter journals reference — replaced with recent iter commit bodies (universal) - Example ideas calibrated to AILang (FizzBuzz, Newton's method on Float, JSON-tree depth, ADT functors) — generalised to "realistic tasks an end-user might be asked to do" - `design/contracts/0004-feature-acceptance.md` cross-ref — dropped (AILang-specific contract); the empirical-vs- prospective brainstorm symmetry survives in prose Universal substance preserved verbatim: - All three Iron Law clauses (public-interface-only, canonical-form-only, record-don't-fix) - Five-phase process structure - Four-class finding taxonomy (bug / friction / spec_gap / working) - Spec template - Status protocol (DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED) - All 8 Common Rationalisations rows (vocabulary-substituted) - All 10 Red Flags bullets (vocabulary-substituted, with the AILang-specific .ail.json hand-write bullet generalised to "intermediate representations") The source-isolation contract (Iron Law clause 1) is the load-bearing discipline. Profile slot `paths.public_interface` makes it machine-checkable; the agent's hard limit on opening paths outside that list is the discipline. |
||
|
|
71fa6a28de |
audit: skill + architect + bencher agents migrated
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.
|
||
|
|
7f46e9c027 |
docwriter: skill + agent migrated; commands.doc_build slot added
Third skill via the boss pattern. docwriter was the most language-coupled of the seven (Rust rustdoc, cargo doc, /// + //!, intra-doc links). Generalised the discipline while keeping Rust as the canonical concrete example, with a note that other languages substitute syntax (TSDoc, Python docstrings, Javadoc). Profile gains one slot: - `commands.doc_build` — doc-build command that prints warnings on stderr (e.g. "cargo doc --no-deps 2>&1"); used by the docwriter agent's verification triple and warning enumeration. Optional — projects without API docs omit it. Vocabulary substitutions: - AILang → "this project" - "crates" → "components / packages / crates / modules" (the project's idiom) - "milestone" → "cycle" - "Boss" → "orchestrator" - "ailang-docwriter" → "docwriter" AILang-specific bits replaced: - `cargo doc --no-deps 2>&1` → `commands.doc_build` slot - `cargo build --workspace` / `cargo test --workspace` → `commands.build` / `commands.test` slots - `crate / module / item` levels → "top-level / module-level / item-level" (the universal taxonomy; concrete syntax via language note) - `src/lib.rs` / `src/main.rs` hardcoded paths → "entry-point file" (Rust example kept inline) - `docs/` / `design/` hardcoded dirs → `paths.design_ledger`, `paths.design_contracts`, `paths.design_models`, `paths.spec_dir` slots Universal substance preserved verbatim: - Iron Law (4 lines) - Documentation rules (5 bullets) — substantive content; only the concrete-syntax examples got the Rust-as-example note - Hard limits (4 bullets) - Verification triple (build / test / doc_build) - Status protocol (DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED) - All 7 Common Rationalisations rows (with vocabulary edits) - All 7 Red Flags bullets |
||
|
|
7715ab44f3 |
debug: skill + debugger agent migrated
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 |
||
|
|
d7256e6f8c |
flatten: skills directly at repo root, no skills/ subdir
~/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. |
||
|
|
9e10e9dfee |
boss: migration pilot — autonomous orchestrator mode generalised
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. |
||
|
|
de26df1727 |
nest agents under their dispatching skill
Top-level agents/ was an arbitrary flat layout from the skeleton commit, with no substantive reason behind it. Mirroring AILang's convention (skills/<name>/agents/<agent>.md) is strictly better: it makes the "no orphan agents" rule structurally true — you cannot place an agent file outside a skill — and it keeps the skill/agent binding visible at first glance. Claude Code's user-level discovery is unaffected: install.sh now symlinks ~/.claude/agents/<name> to skills/<name>/agents/ for each skill that has an agents/ subdirectory. The .claude/ registry stays flat; the source tree stays nested. The two checklists previously living in agents/README.md are folded into skills/README.md. |
||
|
|
253273b007 |
skeleton: plugin layout + docs, skill/agent migration deferred to iter 1
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. |