package-registry

package-registry is a skill for Claude Code from littlebearapps/pitchdocs. It costs 59 tokens per session (1,227 once invoked), scanned A, original, MIT.

A documentation guide for software packages published through npm or PyPI, two public registries for sharing JavaScript and Python packages.

In plain words
What is it for?
Use it to check package metadata, README compatibility, publishing settings, provenance badges, and audit requirements when package.json or pyproject.toml is present.
Why use it?
Registry pages may use package metadata and published files differently from the source repository, so documentation changes can be missed or rendered incorrectly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the pitchdocs plugin — 16 skills, 15 commands, 4 agents shipped together

Install

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.

agentmods
npx agentmods add skills/littlebearapps/pitchdocs/package-registry
Any agent
npx skills add littlebearapps/pitchdocs --skill package-registry
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/pitchdocs

Made for: Claude Code.

Or install pitchdocs, the plugin that ships this one along with the rest of its 16 skills, 15 commands, 4 agents.

Wrote 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.

agentmods badge for package-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/littlebearapps/pitchdocs/package-registry.svg)](https://agentmods.dev/skills/littlebearapps/pitchdocs/package-registry)
Your own site
<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>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 918690720894, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

.claude/skills/package-registry/SKILL.md · 107 lines

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

Read the full file on GitHub · 107 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 107 lines · 59 tokens per session scan A 918690720894

Subscribe to this mod's changes

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.