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.
npx agentmods add instructions/paullukic/coograph/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.svg" alt="Measured on agentmods" 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 | $0.00663 | $0.00663 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
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 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.
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.
<!-- Quick summary for AI agents that auto-read AGENTS.md (VS Code Copilot, OpenAI Codex CLI, OpenCode, generic AGENTS.md-aware agents). Other tools have native config files: .cursor/rules/, .windsurfrules, CONVENTIONS.m How it starts
The opening of the file, as written. The whole thing — 42 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.
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.
Conventions
When working on this codebase:
- Rules: Follow
.github/copilot-instructions.md. - Pre-flight: On session start, call
get_minimal_contextto verify code-graph availability. Code-graph is MANDATORY for ALL navigation — fall back to grep/glob ONLY when the DB is genuinely absent. Checkopenspec/changes/for in-progress work. - OpenSpec gate: Any change that modifies 2+ files, touches a spec, alters a public interface, or adds new behavior MUST go through
openspec/changes/<date>-<slug>/with user approval before code. Exemptions are narrow and literal: typo fix, comment-only edit, user-dictated config bump, or follow-up on an approved in-progress OpenSpec. "Trivial", "obvious", "small" are NOT exemptions. - Stack:
- Structure:
- Communication: Read
.github/instructions/brutal-honesty.instructions.mdat session start and apply throughout. Direct, evidence-based, severity-rated. Every finding citesfile:linewith verbatim quotes. - Workflow: Plan → Propose (OpenSpec) → Apply → Quality Gates → Review Gate → Archive. Skip only for exemptions above. After 3 failed attempts, stop and ask.
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.
- 4d 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 29d ago), licensed MIT. It adds 663 tokens to every session, about $0.0033 per session on Opus 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.
Other instructions, from other repositories
docvet CLAUDE.md
Claude Code instructions for Alberto-Codes/docvet, covering claude.md, project overview, build & development, install in development mode and with optional griffe support.
agent-notify AGENTS.md
AGENTS.md instructions for Akash97p/agent-notify, covering agentnotify agent workflow, start or resume work, local git workflow, required quality gates and architecture and security guardrails.
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).
nexus-mcp CLAUDE.md
Claude Code instructions for jaggernaut007/nexus-mcp, covering nexus-mcp, use nexus-mcp tools before built-in tools, known limitations, structure (all implemented) and commands.
claude-code-second-brain AGENTS.md
Instructions for shofer-dev/claude-code-second-brain, covering agents.md, read first, invariants and working here.
nexus-mcp GEMINI.md
Gemini CLI instructions for jaggernaut007/nexus-mcp: Read AGENTS.md at the repo root — it is the single source of truth for this project (stack, commands, Definition of Done, code standards). Also read PROGRESS.md for current session state before starting work.