mirror of
https://github.com/bmad-code-org/BMAD-METHOD.git
synced 2026-09-19 08:11:52 +08:00
Alex Verkhovsky
eeaaa585ee
* chore(review): swap Augment for Greptile and repair CodeRabbit config Augment is no longer in use, so its guidelines file goes away in favour of greptile.json. Rather than paraphrasing the repo's conventions, both bots are now pointed at the same source files: AGENTS.md and tools/skill-validator.md, plus docs/_STYLE_GUIDE.md scoped to docs. Four CodeRabbit path instructions had gone stale and matched no tracked files: src/**/skills/**, src/**/workflows/**, src/**/tasks/** and src/**/*.agent.yaml. The skill-validator catalog was consequently applied to nothing. Retarget them at src/*-skills/** and src/bmm-skills/agents/**, and drop the two describing layouts the repo no longer has. Three further fixes: `walkthrough: false` is not a schema v2 key, so use collapse_walkthrough; the media filters were root-only globs and left docs/images under review; and the validation-report filter named .md where those files are .html. AGENTS.md gains the prompt-length and testing conventions, which were until now written down nowhere in the repo. CLAUDE.md is unignored and imports it. * chore(review): align catalog scoping and narrow the ignore lists Greptile's global instructions named tools/skill-validator.md and docs/_STYLE_GUIDE.md, but customContext.files supplies those only for skill and documentation paths. Reviewing anything else, Greptile was told to apply catalogs it had not been given — an invitation to invent rules from the filenames. The global clause now names only AGENTS.md, which is loaded on every review; the two scoped catalogs keep their scopes and their own descriptions. website/** was excluding 18 hand-written source files along with the assets — the Astro components and pages, both rehype plugins, the locale and site-url helpers, the i18n JSON. Exclude website/public/** and website/diagrams/** instead, so generated and editor-authored artifacts stay out while the source is reviewed. tools/tests/fixtures/** joins test/fixtures/** ahead of the validator port that moves the skill fixtures there. Those fixtures encode defects deliberately, so any review comment on them is wrong by construction.
53 lines
3.2 KiB
JSON
53 lines
3.2 KiB
JSON
{
|
|
"strictness": 2,
|
|
"commentTypes": ["logic", "syntax"],
|
|
"triggerOnUpdates": false,
|
|
"excludeAuthors": ["dependabot[bot]"],
|
|
"ignorePatterns": "greptile.json\neslint.config.mjs\n.claude/**\n.codex/**\n.agent/**\n.agentvibes/**\n.kiro/**\n.roo/**\n.github/chatmodes/**\ndist/**\nbuild/**\ncoverage/**\n.bundler-temp/**\n**/node_modules/**\n**/*.min.js\n**/*.generated.*\n**/*.bundle.md\npackage-lock.json\n**/*.png\n**/*.jpg\n**/*.svg\ntest/fixtures/**\ntools/tests/fixtures/**\ntest/template-test-generator/**\ntools/template-test-generator/test-scenarios/**\n_bmad*/**\nwebsite/public/**\nwebsite/diagrams/**\nz*/**\nsample-project/**\ntest-project-install/**\n**/validation-report-*.html\nCHANGELOG.md",
|
|
"instructions": "Most of this repo's source is prompt text read by agents at runtime, not executable code. Confine review of it to claims that can be checked against the repository: file paths and cross-references that do not resolve, invocation syntax that does not match the referenced skill, instructions that contradict another file, documented behavior that the code does not implement, and violations of the conventions in AGENTS.md. Do not comment on prompt wording, tone, phrasing, length, or how thorough an instruction feels \u2014 those are authoring decisions and are not yours to judge.",
|
|
"customContext": {
|
|
"files": [
|
|
{
|
|
"path": "AGENTS.md",
|
|
"description": "Repo conventions every change must satisfy"
|
|
},
|
|
{
|
|
"path": "tools/skill-validator.md",
|
|
"description": "Authoritative rule catalog for skills \u2014 SKILL.md metadata, workflow constraints, step file structure, path references, variable resolution, sequential execution, skill invocation syntax. Apply the whole catalog to changed skill files.",
|
|
"scope": ["src/bmm-skills/**", "src/core-skills/**"]
|
|
},
|
|
{
|
|
"path": "docs/_STYLE_GUIDE.md",
|
|
"description": "Documentation conventions: Google style, Diataxis structure, plus project-specific rules on headers, admonitions, and nesting",
|
|
"scope": ["docs/**"]
|
|
}
|
|
],
|
|
"rules": [
|
|
{
|
|
"id": "docs-follow-source",
|
|
"rule": "Source changed. Check whether docs/ needs a matching update \u2014 new features, changed behavior, renamed concepts, altered CLI flags, or modified configuration options should all be reflected in the relevant doc pages. Flag missing or outdated docs.",
|
|
"scope": ["src/**"],
|
|
"severity": "medium"
|
|
},
|
|
{
|
|
"id": "agent-skill-shape",
|
|
"rule": "Agent skill. The persona is configured in customize.toml under [agent]: check that every {agent.*} placeholder the SKILL.md interpolates has a corresponding key there, and that menu entries name skills that exist in this repo.",
|
|
"scope": ["src/bmm-skills/agents/**"],
|
|
"severity": "high"
|
|
},
|
|
{
|
|
"id": "docs-links-resolve",
|
|
"rule": "Check that internal markdown links point at files that exist.",
|
|
"scope": ["docs/**/*.md"],
|
|
"severity": "medium"
|
|
},
|
|
{
|
|
"id": "tooling-exit-codes",
|
|
"rule": "Build and tooling script. Check error handling and that failures exit non-zero.",
|
|
"scope": ["tools/**", "src/scripts/**"],
|
|
"severity": "medium"
|
|
}
|
|
]
|
|
}
|
|
}
|