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.
curl -O https://raw.githubusercontent.com/paullukic/coograph/main/AGENTS.mdgit clone --depth 1 https://github.com/paullukic/coographWrote 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.
[](https://agentmods.dev/instructions/paullukic/coograph/agents-md)<a href="https://agentmods.dev/instructions/paullukic/coograph/agents-md"><img src="https://agentmods.dev/badge/instructions/paullukic/coograph/agents-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.
<a href="https://agentmods.dev/instructions/paullukic/coograph/agents-md"><img src="https://agentmods.dev/badge/instructions/paullukic/coograph/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02544 | $0.02544 |
| Opus 5.5 | $0.01018 | $0.01018 |
| Sonnet 5.5 | $0.00509 | $0.00509 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade C, and why
coograph AGENTS.md scanned grade C 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 11d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Tool-neutral rules. Read automatically by VS Code Copilot, OpenAI Codex CLI, OpenCode and other AGENTS.md-aware agents; Claude Code imports it from CLAUDE.md. Each rule lives in exactly one file: hard rules and work How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Context
Invocation
If the user types /coograph-init, $coograph-init, or asks to "initialize the project" / "set up coograph" / "wire up coograph in this repo", follow .github/skills/coograph-init/SKILL.md exactly. That single procedure is the source of truth across every tool.
If the user types /coograph-doctor, $coograph-doctor, or asks to "check the install" / "run the doctor", follow .github/skills/coograph-doctor/SKILL.md: a read-only health check that offers each fix before applying it.
Note for Codex CLI: / is reserved for built-in commands. The Codex skill at .agents/skills/coograph-init/SKILL.md auto-triggers from description match, or invoke explicitly with $coograph-init.
Hard rules
🛑 HARD RULE — CODE-GRAPH FIRST. Before any codebase search, navigation, tracing, or exploration you MUST use the code-graph MCP tools first (
mcp__code-graph__*). Only fall back tosqlite3 .code-graph/graph.db, and only then toGlob/Grep/Read, if the code-graph DB is genuinely NOT present in the workspace. Convenience is not a valid reason to skip. See § Tool Preferences below.
🛑 HARD RULE — OPENSPEC OR STOP. For any change that modifies 2+ files, touches a spec, alters a public interface, or adds new behavior, you MUST create an OpenSpec in
openspec/changes/<date>-<slug>/and WAIT for user approval BEFORE writing code. Exemptions are narrow and literal:
- Typo fix in a single file
- Comment/docstring-only edit
- Config-value bump the user explicitly dictates (e.g., "set X=2")
- Follow-up fix for an already-approved, in-progress OpenSpec
"Trivial," "obvious," "I already know what to do," "small," and "just one tweak" are NOT exemptions. If in doubt → propose, don't code. See § Workflow below.
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.
- 11d ago Changed · +2 lines · +57 tokens per session 5840ddba0140
- 1mo ago Changed · +76 lines · +1,729 tokens per session 86b6cd7bdc44
- 1mo ago Changed · +2 lines · +95 tokens per session b53da13f647c
- 2mo ago First seen · 42 lines · 663 tokens per session scan C 6f57b1a53ba0
coograph AGENTS.md is an instructions file published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 2,544 tokens to every session, about $0.0102 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
coograph AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coograph AGENTS.mdpaullukic/coograph | Instructions file | 17 | 12d ago | MIT | C | 2,544 | Codex, OpenCode |
| 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 |