What is coograph CLAUDE.md?

Project instructions for Coograph, a codebase that requires agents to use a code-graph database before other search methods and to propose an OpenSpec before most multi-file or behavior-changing edits.

Use them when working in the Coograph repository, especially for code navigation, changes affecting multiple files, public interfaces, specifications, or new behavior.

They give the agent project-specific rules for exploring code, requesting approval, communicating, and managing branches before making changes.

How paullukic/coograph configures Claude Code

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.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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/paullukic/coograph/claude-md/github.svg)](https://agentmods.dev/instructions/paullukic/coograph/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/paullukic/coograph/claude-md"><img src="https://agentmods.dev/badge/instructions/paullukic/coograph/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/paullukic/coograph/claude-md"><img src="https://agentmods.dev/badge/instructions/paullukic/coograph/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 608 This file is loaded in full into every session.

When invoked 608 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00608	$0.00608
Opus 5.5	$0.00243	$0.00243
Sonnet 5.5	$0.00122	$0.00122
Haiku 4.5	$0.00061	$0.00061

Measured 1mo ago against content hash 361de923400f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coograph CLAUDE.md 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.

CLAUDE.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

@AGENTS.md @.github/copilot-instructions.md

The two imports above hold the hard rules, workflow, commands, routing, and code conventions. Each rule is stated once, there. This file adds only what is specific to Claude Code.

Claude Code specifics

Instruction files. Domain rules in .github/instructions/ load automatically in VS Code; in Claude Code read them on demand (testing.instructions.md when writing tests, styling.instructions.md when writing CSS). A workspace with its own AGENTS.md gets a one-line CLAUDE.md holding @AGENTS.md, which Claude Code loads only when you touch files there.
Gotchas. A hook puts the GOTCHAS.md entries that match a file you edit or a command you run in front of you, once per session. Treat them as rules for that call.
Retro. Sessions are measured against the hard rules (see .github/retro/README.md). When the session-start line says run /coograph-retro, mention it to the user once. Never run it unprompted.

Subagent Delegation

Situation	Command
Code review or convention audit	`/coograph-review`
Deep review of a big change before approvals (multi-agent, adversarial; optional, costly): full PR, fix batch (delta) or a plan before code	`/coograph-ultra-review`
Bug investigation, build errors	`/coograph-debug`
Planning / unclear requirements	`/coograph-plan`
Completion evidence, verification	`/coograph-verify`
Codebase search, research	`/coograph-search`
Guardrail retro, instruction and hook tuning from evidence	`/coograph-retro`
Instruction files over budget (`layout.py --budget` says STRUCTURAL)	`/coograph-docs-restructure`

Pass the full task description and relevant file paths when delegating. Claude Code subagents do receive their tools, so the hand-off rule in AGENTS.md does not apply here.

Context Management

Preservation on compaction

When the conversation context is compacted, always preserve:

The current task from tasks.md (if working through an OpenSpec)
The full list of files modified in this session
Any failing test or build output not yet resolved
Acceptance criteria for the current task
Any user decisions or scope changes made during this session

Read the full file on GitHub · 41 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.

1mo ago Changed · -109 lines · -1,928 tokens per session 361de923400f
1mo ago Changed · +1 lines · +124 tokens per session e025dcb60515
1mo ago Changed · +3 lines · +121 tokens per session 14a3b34be528
2mo ago First seen · 146 lines · 2,291 tokens per session scan A fc8166870769

Subscribe to this mod's changes

coograph CLAUDE.md is an instructions file published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 608 tokens to every session, about $0.0024 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 2026-08-30.

Git and workflow Planning ai-agents ai-coding ai-optimization ai-tools code-graph token-ai-optimizator

coograph CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
coograph CLAUDE.mdpaullukic/coograph	Instructions file	17	12d ago	MIT	A	608	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

coograph: Instructions file for Claude Code