agentmods.dev

opensrc

opensrc is a skill for Claude Code from andreasasprou/agent-skills. It costs 29 tokens per session (387 once invoked), scanned C, original, MIT.

A tool for downloading the source code of npm packages, which are reusable JavaScript and TypeScript libraries. It is intended for inspecting how a library works internally when its documentation and type definitions are not enough.

In plain words
What is it for?
Use it to fetch package source, locate relevant functions or files, and study library internals during debugging or development.
Why use it?
It helps explain unexpected library behavior and reveals implementation patterns that public documentation may not show. It also supports inspecting packages inside monorepos, which are repositories containing multiple related packages.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the opensrc plugin — 1 skill shipped together

not rated 7repo 4mo ago C scan 29 tokens original MIT

Good fit Use it to fetch package source, locate relevant functions or files, and study library internals during debugging or development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andreasasprou/agent-skills/opensrc
View source ↗ andreasasprou/agent-skills
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.

Any agent
npx skills add andreasasprou/agent-skills --skill opensrc
Clone the repo
git clone --depth 1 https://github.com/andreasasprou/agent-skills

Made for: Claude Code.

Or install opensrc, the plugin that ships this one along with the rest of its 1 skill.

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 opensrc

README.md
[![agentmods](https://agentmods.dev/badge/skills/andreasasprou/agent-skills/opensrc/github.svg)](https://agentmods.dev/skills/andreasasprou/agent-skills/opensrc)
Your own site
<a href="https://agentmods.dev/skills/andreasasprou/agent-skills/opensrc"><img src="https://agentmods.dev/badge/skills/andreasasprou/agent-skills/opensrc/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for opensrc

Your own site · 80×15
<a href="https://agentmods.dev/skills/andreasasprou/agent-skills/opensrc"><img src="https://agentmods.dev/badge/skills/andreasasprou/agent-skills/opensrc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 387 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00029 $0.00387
Opus 5.5 $0.00012 $0.00155
Sonnet 5.5 $0.00006 $0.00077
Haiku 4.5 $0.00003 $0.00039

Measured 2mo ago against content hash a4bed2b28386, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

opensrc scanned grade C with 1 finding 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf opensrc/<package>
plugins/opensrc/skills/opensrc/SKILL.md · 68 lines

What it actually says

opensrc

Fetch npm package source code locally when you need to understand implementation details.

When to Use

  • Debugging unexpected library behavior
  • Understanding internal patterns before extending a library
  • Types/docs are insufficient

Commands

# Fetch package(s)
npx opensrc <package>
npx opensrc ai zod @anthropic-ai/sdk

# Check what's fetched
cat opensrc/sources.json

# Clean up when done
rm -rf opensrc/<package>

Exploration Pattern

# 1. Fetch
npx opensrc ai

# 2. Check structure (many are monorepos)
ls opensrc/ai/packages/

# 3. Find what you need
grep -r "functionName" opensrc/ai/src/

# 4. Read the implementation
# (use Read tool)

# 5. Clean up
rm -rf opensrc/ai

Tips

  • Check sources.json first - don't re-fetch what's already there
  • Target specific files - don't read entire packages
  • Monorepos: Check packages/ directory for subpackages
  • Clean up - source code takes disk space, remove when done

Common Packages

Package Structure
ai Monorepo: packages/anthropic/, packages/openai/, etc.
@anthropic-ai/sdk Single package: src/
zod Single package: src/types/
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. 2mo ago First seen · 68 lines · 29 tokens per session scan C a4bed2b28386

Subscribe to this mod's changes

opensrc is a skill published in the GitHub repository andreasasprou/agent-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 387 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research
Related

opensrc compared with skills from other repositories

opensrc next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opensrcandreasasprou/agent-skillsSkill74mo agoMITC29Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code