agent-config-lintlisted

# Agent config lint Agent config fails quietly. A `SKILL.md` points at a script that was renamed, an `AGENTS.md` hardcodes the author's home directory, two skills describe themselves so similarly the agent picks the wrong one. Nothing throws — the agent just does the wrong thing, and only on someone else's machine. This skill runs `tenken`, which bundles three zero-dependency linters in one pass. ## When to use Run it when any of these is true: - about to commit or publish a `SKILL.md`, `AGENTS.md`, `CLAUDE.md` or `llms.txt` - about to publish a skill to ClawHub - a skill works for the author but not for a teammate - a skill is not firing, or the wrong skill fires - the user asks to review or check agent config ## How to run ```bash npx @hyuga/tenken ``` Scan a specific path: ```bash npx @hyuga/tenken path/to/skills ``` Machine-readable output, for when you need to act on individual findings: ```bash npx @hyuga/tenken --format json ``` Exit code is `0` when clean, `1` when there is at least one error, `2` on bad usage. Warnings do not fail unless `--strict` is passed. ## What it catches | | | |---|---| | a back-quoted path or markdown link that does not resolve | reference rot | | `/Users/<name>/…`, `C:\Users\<name>\…` | will not resolve for anyone else | <!-- carry-ignore --> | an external CLI the document never declares or installs | missing dependency | | an unresolved `<FILL_ME>` / `REPLACE_ME` left in a shipped file | unfinished | <!-- carry-ignore --> | fr