github-code-search

A search tool for finding exact code patterns across about one million public GitHub repositories, using grep.app, a public code-search service.

In plain words
What is it for?
Use it to look up real API usage, configuration keys, error messages, stack frames, and prior implementations in public code.
Why use it?
It helps you find existing examples and common approaches before writing custom code, while keeping private or sensitive searches out of the service.

Skill for Claude CodeCodex

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/dryvist/claude-code-plugins/github-code-search
Any agent
npx skills add dryvist/claude-code-plugins --skill github-code-search
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,033 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00076 $0.01033
Opus 5 $0.00038 $0.00517
Sonnet 5 $0.00015 $0.00207
Haiku 4.5 $0.00008 $0.00103

Measured yesterday against content hash 8dc143c9398b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-code-search scanned grade A 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s 'https://grep.app/api/search?q=fetchGitTree&l=Nix' \
github-workflows/skills/github-code-search/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Code Search (grep.app)

Literal code search across roughly a million public GitHub repositories. This is the fastest way to answer "has someone already done this?" — which is the question that has to be answered before any custom code gets written.

When to reach for it

  • Before writing anything custom. native-first says find the existing solution first; this is how you look. A pattern with thousands of hits is idiomatic; a pattern with three is probably a mistake.
  • Real usage of an API, flag, or config key the docs mention but do not show.
  • Prior art for a design decision — how five projects structured the same thing.
  • Error strings and stack frames — searching the literal message often lands on the upstream source that emits it.

Not for: searching this repo (use Grep), private code, or anything where the query itself is sensitive. The query string leaves the machine. Never put a hostname, credential, internal path, or customer name in a search.

How it searches

grep.app matches literal code, not keywords. It is grep over a corpus, not a search engine — there is no stemming, no synonyms, no ranking by intent. Search the exact characters you expect to be in the file.

good:  useOptimistic(          bad:  react optimistic update hook
good:  ANSIBLE_HOST_KEY_CHECKING       bad:  how to disable ansible host key checking

Primary path — the grep MCP server

One tool: mcp__grep__searchGitHub.

Param Type Notes
query string required — the literal code to find
language string[] e.g. ["TypeScript","TSX"], ["Nix"], ["YAML"]
repo string partial match — vercel/ matches the whole org
path string partial match — /flake.nix, /.github/workflows/
useRegexp bool default false; prefix (?s) for multi-line patterns
matchCase bool default false
matchWholeWords bool default false — set it when a short identifier is a substring of everything

Read the full file on GitHub · 96 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. yesterday First seen · 96 lines · 76 tokens per session scan A 8dc143c9398b

Subscribe to this mod's changes

github-code-search is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 1,033 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

rspec

This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…

hoblin/claude-ruby-marketplace · 125 tokens

activerecord

This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…

hoblin/claude-ruby-marketplace · 180 tokens

draper-decorators

This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…

hoblin/claude-ruby-marketplace · 131 tokens

mcp-server

This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…

hoblin/claude-ruby-marketplace · 98 tokens

ratatui-ruby

This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…

hoblin/claude-ruby-marketplace · 119 tokens

dragonruby

This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…

hoblin/claude-ruby-marketplace · 100 tokens