opensrc-research

opensrc-research is a skill for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 80 tokens per session (1,028 once invoked), scanned A, original, MIT.

A research tool that fetches the actual source code of a third-party package and lets you search it. Third-party packages are libraries maintained outside your project, such as npm, PyPI, NuGet, or Rust packages.

In plain words
What is it for?
Use it to check how a library works, verify whether it supports a feature, confirm an API, or search a dependency's source during code review.
Why use it?
It replaces guesses and possibly outdated documentation with evidence from the package's source. This helps verify what an API or dependency really does before answering questions or reviewing code.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the nuget-opensrc plugin — 1 skill, 1 command shipped together

Good fit Use it to check how a library works, verify whether it supports a feature, confirm an API, or search a dependency's source during code review.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ANcpLua/ancplua-claude-plugins
Claude Code
/plugin install nuget-opensrc

Made for: Claude Code.

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

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-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/opensrc-research/github.svg)](https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/opensrc-research)
Your own site
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/opensrc-research"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/opensrc-research/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-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/opensrc-research"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/opensrc-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00080 $0.01028
Opus 5.5 $0.00032 $0.00411
Sonnet 5.5 $0.00016 $0.00206
Haiku 4.5 $0.00008 $0.00103

Measured 1mo ago against content hash da8bc3a61e82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opensrc-research 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 1mo 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.

plugins/nuget-opensrc/skills/opensrc-research/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

opensrc-research

Quickstart

One command grounds an answer: resolve the package's real source path, then search it.

rg "useQuery" "$(opensrc path @tanstack/react-query)"

opensrc path prints the on-disk checkout (fetching on first use); rg greps it for the symbol you're about to make a claim about. Everything below is variations on this shape.

When to fire

Fire this skill whenever the next answer would otherwise be a guess about how a dependency behaves. Signals:

  • "Does library X support Y?" / "How does X actually do Y?"
  • "Is the doc claim about X accurate?"
  • "Grep for Z in package W"
  • Borderline confidence answering an API question — about to write [unverified]
  • Code under review imports a package and you want to ground a review comment in actual source

The grounded-answer workflow

  1. Identify the package shape:

    Shape Form Example
    npm package bare name opensrc path zod
    PyPI package pypi: prefix opensrc path pypi:requests
    Rust crate crates: prefix opensrc path crates:serde
    NuGet package use the wrapper "${CLAUDE_PLUGIN_ROOT}/bin/nuget-opensrc" path Microsoft.Extensions.Logging
    GitHub repo owner/repo (drifts with main) opensrc path open-telemetry/opentelemetry-dotnet
    GitHub repo at commit owner/repo#<sha> (pinned) opensrc path dotnet/runtime#abc123
  2. Fetch and grep:

    # NuGet (commit-pinned — preferred for .NET work):
    PKG_PATH="$("${CLAUDE_PLUGIN_ROOT}/bin/nuget-opensrc" path Microsoft.AspNetCore.Authentication.JwtBearer)"
    rg "JwtBearerEvents" "$PKG_PATH"
    
    # npm / PyPI / crates / GitHub:
    rg "parseAsync" "$(opensrc path zod)"
    
  3. Cite findings as file:line references, not paraphrases. The whole point is grounding — quote what's actually in the source.

  4. If using bare GitHub form, the result is the default branch and drifts with main. To pin to a specific tag after fetching:

    cd "$(opensrc path open-telemetry/opentelemetry-dotnet)" && git checkout v1.10.0
    

Read the full file on GitHub · 78 lines

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. 1mo ago First seen · 78 lines · 80 tokens per session scan A da8bc3a61e82

Subscribe to this mod's changes

opensrc-research is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 1,028 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-01.

Related

opensrc-research compared with skills from other repositories

opensrc-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opensrc-researchANcpLua/ancplua-claude-pluginsSkill62d agoMITA80Claude Code
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k7d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code