source-search

source-search is a skill for Claude Code, Codex from pilinux/gorest. It costs 27 tokens per session (280 once invoked), scanned A, original, MIT.

A read-only repository search workflow for finding where code symbols, text, environment variables, or error codes are defined and used. It returns the most relevant file paths and line numbers.

In plain words
What is it for?
Use it to locate a class, function, route, configuration variable, error message, or every place a value is referenced.
Why use it?
It avoids manually searching a large codebase and helps identify the main file to inspect first. It also reduces noise by narrowing searches to relevant folders or file types.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to locate a class, function, route, configuration variable, error message…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pilinux/gorest/source-search
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 pilinux/gorest --skill source-search
Clone the repo
git clone --depth 1 https://github.com/pilinux/gorest

Made for: Claude Code, Codex.

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 source-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/pilinux/gorest/source-search.svg)](https://agentmods.dev/skills/pilinux/gorest/source-search)
Your own site
<a href="https://agentmods.dev/skills/pilinux/gorest/source-search"><img src="https://agentmods.dev/badge/skills/pilinux/gorest/source-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 280 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 $0.00027 $0.00280
Opus 5 $0.00014 $0.00140
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 7d ago against content hash 550971e03e6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

source-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 7d 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.

.agents/skills/source-search/SKILL.md · 42 lines

What it actually says

When to Use

  • You need to locate where a symbol, string, env var, or error code is defined or referenced across the codebase.

Rules

  • Read-only: do not modify files.
  • Prefer grep for broad discovery, then targeted read for the best matches.
  • Narrow with glob patterns to reduce noise.

Workflow

  1. Identify exact search keys and likely variants.
  2. Glob by folder or pattern to limit scope.
  3. Grep and rank results by relevance.
  4. Return top matches with path:line and a short note.

Output

  • Definitions and top usages with path:line citations.
  • Brief note on next steps or likely primary file to inspect.

Examples

  • "Where is PrefixJtiBlacklist defined?" - search config/ for the constant.
  • "Which files reference ACTIVATE_JWT?" - grep across config/, setTestEnv.sh, .env.sample.
  • code-navigation (impact mapping), file-reader (detailed read)
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. 7d ago First seen · 42 lines · 27 tokens per session scan A 550971e03e6d

Subscribe to this mod's changes

source-search is a skill published in the GitHub repository pilinux/gorest (504 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 280 once invoked, about $0.0001 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 2026-08-30.