validate-agents-entry
Require root AGENTS.md with a bounded line count so the agent entry stays a small map. Runs in check:all.
- License 许可
- MIT
- 所属仓库
- midyan/skissue
- 最近更新
- 2026-05-18
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- validate-agents-entry
- description
- Require root AGENTS.md with a bounded line count so the agent entry stays a small map. Runs in check:all.
02 资源文件 1
- 参考文档INDEX.md271 B
03 SKILL.md 正文
validate-agents-entry (soft)
Enforces harness navigation: a non-empty AGENTS.md at the repo root and a maximum line count (default 200) so content stays a map (links to docs/, INDEX.md), not an encyclopedia.
See hard/README.md for rules and AGENTS_MAX_LINES.
04 同仓库更多 Skills
validate-shell-exec
Restrict child_process.spawn/exec to approved modules (e.g. shell/tmux helpers) so subprocess usage stays centralized.
validate-registry-hard
Validates registry.json shape and that each skill path contains SKILL.md at the skill root.
validate-registry
Keep root registry.json consistent with on-disk skill folders so installs and docs do not drift.
validate-naming
Enforce kebab-case filenames and PascalCase type names under src/; reports naming drift for consistency.
validate-logging
Prefer structured logging over raw console.* outside approved CLI entrypoints; keeps observability consistent.
validate-links
Scan markdown for broken relative links across the repo. Run via npm run check:links or the harness hard skill.