Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/littlebearapps/pitchdocs/package-registrynpx skills add littlebearapps/pitchdocs --skill package-registrygit clone --depth 1 https://github.com/littlebearapps/pitchdocsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/littlebearapps/pitchdocs/package-registry)<a href="https://agentmods.dev/skills/littlebearapps/pitchdocs/package-registry"><img src="https://agentmods.dev/badge/skills/littlebearapps/pitchdocs/package-registry.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01227 |
| Opus 5 | $0.00030 | $0.00613 |
| Sonnet 5 | $0.00012 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
package-registry scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package Registry Documentation Guidance
When This Applies
These checks are conditional — only run when the project is published to a package registry.
| File Present | Registry | Action |
|---|---|---|
package.json |
npm (npmjs.com) | Check npm metadata fields, badge templates |
pyproject.toml |
PyPI (pypi.org) | Check PyPI metadata fields, Markdown compatibility |
| Both | npm + PyPI | Check both; cross-renderer compatibility is critical |
Detection:
[ -f "package.json" ] && echo "npm project detected"
[ -f "pyproject.toml" ] && echo "PyPI project detected"
npm Registry Metadata
The README displayed on npmjs.com comes from the published tarball, not live from GitHub. Changes to your README on GitHub do not update the npm page until you publish a new version.
See SKILL-reference.md for the full package.json field table and always-included files list.
PyPI Registry Metadata
See SKILL-reference.md for the full pyproject.toml field table, well-known URL labels, and PEP 639 SPDX licence guidance.
Verified vs Unverified Details
PyPI's sidebar splits project information into two sections:
- Verified details (green checkmark): URLs verified through Trusted Publisher. GitHub statistics (stars, forks) only shown here.
- Unverified details: URLs and metadata that cannot be automatically verified.
Configuring a Trusted Publisher automatically verifies the repository URL.
README Cross-Renderer Compatibility
READMEs render on multiple platforms. What works on GitHub may break on npm or PyPI.
| Markdown Feature | GitHub | npm | PyPI | Workaround |
|---|---|---|---|---|
Heading anchors (#section) |
Yes | Yes | No | Use full URLs to GitHub README |
Relative images (./docs/img.png) |
Yes | No | No | Use absolute raw.githubusercontent.com URLs |
GitHub callouts ([!NOTE]) |
Yes | No | No | Use bold text or blockquotes |
<details>/<summary> |
Yes | Yes | Unreliable | Avoid for critical content |
colspan/rowspan in tables |
Partial | Partial | No | Use simpler table structures |
<div align="center"> |
Yes | Yes | No | Acceptable loss; PyPI strips most HTML alignment |
| Mermaid diagrams | Yes | No | No | Use pre-rendered SVG/PNG images |
Task lists (- [ ]) |
Yes | Yes | No | Use bullet lists with emoji checkmarks |
| Footnotes | Yes | No | No | Use inline parenthetical notes |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 107 lines · 59 tokens per session scan A 918690720894
package-registry is a skill published in the GitHub repository littlebearapps/pitchdocs (8 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,227 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
golden-epub
Use when testing the epub golden build.
golden-jupyter-dir
Use when testing the goldenjupyterdir golden build.
golden-man-kw
Use when testing the man golden build.
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.