# Packaged

> Fixture skill for the package-closure check. Use when exercising validate_harness.py against a plugin-packaged skill.

- Skill: `tjdwls101010/packaged` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add tjdwls101010/packaged`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tjdwls101010/packaged/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tjdwls101010 (https://skillmd.com/u/tjdwls101010)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tjdwls101010/packaged

---


# Packaged

Target-project paths — these name files in the repo this skill is *run against*,
which is what it exists to build, so none of them are pointers into its own
package: `.claude/settings.json`, `.claude/rules/*.md`, `CLAUDE.md`, a monorepo's
`packages/api/CLAUDE.md`, another tool's `.github/copilot-instructions.md`, a
vendored `node_modules/some-pkg/README.md`, generated output in `dist/index.md`,
and wherever the reader keeps `docs/notes.md`. None of those resolve here, which
is exactly why they are talking about somewhere else.

Real pointers, which resolve inside the package: references/real.md and
scripts/tool.py.

Leaks — both resolve in this repo and travel nowhere: the rationale is in
docs/design/notes.md and the decision log is in notes/internal-decisions.md.