coograph: Command for Claude Code

.claude/commands/coograph-search.md

coograph-search is a command for Claude Code from paullukic/coograph. It costs 0 tokens per session (673 once invoked), scanned A, original, MIT.

A read-only command for searching a codebase and answering questions with evidence. It explores files and dependencies but does not edit code or implement changes.

In plain words
What is it for?
Use it to locate definitions and usages, trace how a feature works, or map data flow across files at a chosen level of thoroughness.
Why use it?
It helps you understand where code lives and how it works without accidentally changing the project.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is paullukic/coograph's own configuration. It tells Claude Code how to work on coograph itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything coograph configures →

Reuse

Borrowing it

Nothing to install: this file belongs to paullukic/coograph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/paullukic/coograph/main/.claude/commands/coograph-search.md
Clone the repo
git clone --depth 1 https://github.com/paullukic/coograph

Made for: Claude Code.

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 coograph-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/paullukic/coograph/coograph-search/github.svg)](https://agentmods.dev/commands/paullukic/coograph/coograph-search)
Your own site
<a href="https://agentmods.dev/commands/paullukic/coograph/coograph-search"><img src="https://agentmods.dev/badge/commands/paullukic/coograph/coograph-search/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 coograph-search

Your own site · 80×15
<a href="https://agentmods.dev/commands/paullukic/coograph/coograph-search"><img src="https://agentmods.dev/badge/commands/paullukic/coograph/coograph-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 673 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 $0.00000 $0.00673
Opus 5 $0.00000 $0.00336
Sonnet 5 $0.00000 $0.00135
Haiku 4.5 $0.00000 $0.00067

Measured 9d ago against content hash a113a7ab52ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

coograph-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 9d 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.

.claude/commands/coograph-search.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fast read-only codebase search and Q&A. Answer the question below with evidence. You explore — you do not edit files or implement changes.

Thoroughness Levels

The caller specifies one — default to medium if unspecified:

  • Quick: 1-2 targeted searches. For "where is X?" or "what type does Y return?"
  • Medium: Search broadly, read relevant files, cross-reference. For "how does feature X work?" or "find all usages of Y."
  • Thorough: Exhaustive — walk every file in scope, trace call chains, map dependencies. For "audit all places that do X" or "map the data flow from A to Z."

Phase 0 — Orient with Code-Graph (MANDATORY — non-negotiable)

Before reading any file or running any search, this is the HARD RULE — code-graph first, no exceptions:

  1. Call get_minimal_context(task="<question being explored>"). ALWAYS start here. Use the returned file list as your starting point; read only those files.
  2. Fall back to sqlite3 .code-graph/graph.db ONLY when the MCP code-graph server is not registered (tools literally do not exist) OR every attempted MCP call returned an error.
  3. Fall back to Grep/Glob/Read ONLY when Step 1 AND Step 2 are both impossible because the code-graph DB is absent from the workspace.

"Slow", "unwieldy", "I already know the file", or "it's a simple lookup" are NOT valid reasons to bypass. Additional queries: query_graph("callers_of", fn), query_graph("importers_of", file).

Protocol

  1. Understand what the caller needs and what format to return.
  2. Search efficiently (after Phase 0):
    • Grep for exact text/regex matches.
    • Glob for files by name/path pattern.
    • Read files for code (use large ranges — avoid many small reads).
  3. Report with evidence: every claim cites file:line with a verbatim code quote.
  4. Stay in scope: answer what was asked. Do not suggest improvements unless explicitly asked.

Output Structure

  1. Summary (1-3 sentences directly answering the question)
  2. Evidence (file:line references with verbatim code quotes)
  3. Details (additional context, related findings, counts — only if needed)

Read the full file on GitHub · 51 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. 9d ago First seen · 51 lines · 0 tokens per session scan A a113a7ab52ab

Subscribe to this mod's changes

coograph-search is a command published in the GitHub repository paullukic/coograph (17 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 673 tokens. 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.