code-search

code-search is a skill for Claude Code, Codex from MadAppGang/magus. It costs 44 tokens per session (2,242 once invoked), scanned A, original, MIT.

A code-search method for finding code by meaning, structure or exact text, then reading only the relevant returned sections. It includes searches for symbols, implementations, callers, dependencies and impact when the underlying search system supports them.

In plain words
What is it for?
Use it to locate symbols, understand behaviour, trace callers, find implementations, inspect dependencies, or search a codebase before opening several files.
Why use it?
It reduces the need to open many unrelated files and helps choose a search method that matches the question. It also makes unsupported search operations explicit instead of pretending they worked.

Skill for Claude CodeCodex

Part of the code-analysis plugin — 3 skills, 3 commands, 1 agent, 1 hook 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/madappgang/magus/code-search
Any agent
npx skills add MadAppGang/magus --skill code-search
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/magus

Made for: Claude Code, Codex.

Or install code-analysis, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 agent, 1 hook.

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 code-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/madappgang/magus/code-search.svg)](https://agentmods.dev/skills/madappgang/magus/code-search)
Your own site
<a href="https://agentmods.dev/skills/madappgang/magus/code-search"><img src="https://agentmods.dev/badge/skills/madappgang/magus/code-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,242 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 $0.00044 $0.02242
Opus 5 $0.00022 $0.01121
Sonnet 5 $0.00009 $0.00448
Haiku 4.5 $0.00004 $0.00224

Measured 4d ago against content hash c9193b8d4eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-search 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 4d 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/code-analysis/skills/code-search/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrieval is cheap, reading is expensive. Every rule here moves work from the second into the first.

The tool surface

Tool Present Arguments
code_search always query (free-form), intent, scope
find_dependencies, find_dependents, call_tree, find_implementations, impact only when the configured engine genuinely supports the operation symbol, depth / max_depth, scope
Read, Grep, Glob always

Read the tool list; never assume a structural tool exists. Absence means the engine cannot answer that class of question at all — not that it would be slow or approximate. When a tool you wanted is missing, say so in the report and answer with what is present.

code_search infers the intent from the query, so write the real question rather than a hint. Pass intent only to override an inference you have watched go wrong.

Every response names the capability that served it. Read that field — it teaches the routing by example at no cost, and it is how you notice a substitution.

Classify before you query

The request asks for Kind Route to
meaning, behaviour or a flow — "how does authentication work", "how does user data reach the database" conceptual code_search
the shape of the system, or where a named symbol lives and what it touches — "map the service layer", "find class UserService", "who calls parse" structural code_search, then the structural tools
an exact literal, an occurrence count or a filename pattern — "find DEPRECATED_FLAG", "how many TODO comments", "all *.config.ts" lexical Grep / Glob

Locating a named symbol is structural, not lexical. Searching text for a class name returns every mention — comments, strings, imports — unranked, and still misses re-exports. Ask for the definition instead.

Lexical tools are the correct tool for the lexical row. That is routing, not a fallback and not a violation, and it needs no approval. What is forbidden is doing it silently: name the method you used.

Read the full file on GitHub · 177 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. 4d ago First seen · 177 lines · 44 tokens per session scan A c9193b8d4eb4

Subscribe to this mod's changes

code-search is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 2,242 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens