OpeItcLoc03/skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(agents-canon): AGENTS.md canon everywhere — bootstrap v2.0.0 writes AGENTS.md + CLAUDE.md pointer; 15 skills retarget triggers/rule refs from CLAUDE.md to AGENTS.md (semver bumps); dist rebuilt

Browse Source
This commit is contained in:
vitya
2026-08-12 20:36:25 +03:00
parent 6a33542d81
commit e431e9e142
41 changed files with 134 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
skills/project-bootstrap/README.md
View File

@@ -2,7 +2,7 @@
Initializes or upgrades a project workspace in one pass: git, `.gitignore`,
`README.md`, `.wiki/` (Karpathy's LLM Wiki layout), `.tasks/` (per-task board),
and `CLAUDE.md` with skill triggers.
and `AGENTS.md` (canon) with skill triggers + `CLAUDE.md` legacy pointer.
Operates in two modes, picked automatically:
@@ -44,23 +44,24 @@ projects bootstrapped at different times debuggable.
| `README.md` | minimal stub | Skipped if file exists. |
| `.wiki/` | delegated to `setup-wiki` | Karpathy LLM Wiki layout — `CLAUDE.md`, `index.md`, `log.md`, `overview.md`, `raw/`, `entities/`, `concepts/`, `packages/`, `sources/`. |
| `.tasks/` | delegated to `setup-tasks` | Canonical board — `STATUS.md` plus per-task `<task-slug>.md` files. |
| `CLAUDE.md` | `assets/CLAUDE.md.template` | Skill triggers (`use project wiki`, `use task management system`, etc.). On non-Windows hosts, swap the `we're on Windows` line for `we're on Linux` / `we're on macOS`. On upgrade, the template is treated as a canonical set and merged idempotently — only missing trigger lines are appended after user confirm. Re-runs are no-ops. |
| `AGENTS.md` | `assets/AGENTS.md.template` | **Canon** — skill triggers (`use project wiki`, `use task management system`, etc.). On non-Windows hosts, swap the `we're on Windows` line for `we're on Linux` / `we're on macOS`. On upgrade, the template is treated as a canonical set and merged idempotently — only missing trigger lines are appended after user confirm. Re-runs are no-ops. |
| `CLAUDE.md` | generated pointer | `Canon is AGENTS.md. Read AGENTS.md.` — legacy pointer for tooling that looks for the old name. |
| `.wiki/concepts/bootstrap-manifest.md` | generated | Records which skill versions initialized the project, so cross-project layout drift is debuggable. |
## Workflow
1. **Detect mode.** Inspect the current directory — git, `.wiki/`, `.tasks/`,
`CLAUDE.md`, `README.md` — and print a single summary block: what was
`AGENTS.md`, `CLAUDE.md`, `README.md` — and print a single summary block: what was
found, what will be created, what will be skipped.
2. **Confirm.** One question, one confirmation. Nothing is written before the
user agrees.
3. **Steps 1–5.** Create or skip each piece in order — git, README, `.wiki/`,
`.tasks/`, `CLAUDE.md`. Steps 3 and 4 delegate to the setup-skills.
`.tasks/`, `AGENTS.md` + `CLAUDE.md` pointer. Steps 3 and 4 delegate to the setup-skills.
4. **Step 5.5.** Write `bootstrap-manifest.md` recording the versions of
`project-bootstrap`, `setup-wiki`, `setup-tasks`, `project-discipline`,
`setup-interns`, and `using-interns` used.
5. **Step 5.6.** Skill dependencies check. Walk the canonical trigger list
in `CLAUDE.md`, look each up in an embedded `trigger → fulfiller` map,
in `AGENTS.md`, look each up in an embedded `trigger → fulfiller` map,
detect what's missing on this host (`~/.claude/skills/<name>/SKILL.md`
for skills, `~/.claude/plugins/installed_plugins.json` for plugins),
and print one chat-only block listing every missing fulfiller with a