agentmods.dev

coograph: Command for Claude Code

.claude/commands/coograph-init.md

coograph-init is a command for Claude Code from paullukic/coograph. It costs 0 tokens per session (1,136 once invoked), scanned A, original, MIT.

A project setup command that creates a Coograph template and fills it using the project's detected technology and structure. Coograph is a project documentation and code-structure setup system.

In plain words
What is it for?
Asking setup questions, inspecting manifest files and source folders, detecting the tech stack, requesting confirmation, and copying the selected Coograph configuration into a project.
Why use it?
It avoids manually gathering the project's language, framework, testing tools, build commands, and conventions before setting up shared project files.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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 →

not rated 17repo changed 11d ago A scan 0 tokens original MIT
View source ↗ paullukic/coograph coograph.com
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-init.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-init

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/paullukic/coograph/coograph-init"><img src="https://agentmods.dev/badge/commands/paullukic/coograph/coograph-init.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 1,136 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 $0.01136
Opus 5.5 $0.00000 $0.00454
Sonnet 5.5 $0.00000 $0.00227
Haiku 4.5 $0.00000 $0.00114

Measured 11d ago against content hash 3c80068d9e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coograph-init 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 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.

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-init.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize a new project with this Coograph template. Interactive setup that auto-detects the tech stack and fills all placeholders.

The full procedure is in .github/skills/coograph-init/SKILL.md. Follow those steps exactly, with these Claude Code-specific substitutions:

SKILL.md tool Claude Code equivalent
vscode_askQuestions Ask the user directly in the conversation
manage_todo_list Use task tracking internally
apply_patch / create_file Use Edit / Write tools
read_file Use Read tool
grep_search Use Grep tool

Steps (summary)

  1. Gather info — Ask the user: target project path, which AI tools to set up (multi-select: Claude Code, VS Code Copilot, Codex CLI, OpenCode, Cursor, Devin Desktop, Aider, Cline), sections to skip, project-specific rules, whether to enable code-graph, and whether to add global gitignore entries.

  2. Detect tech stack — Read the target project's manifest files (package.json, pom.xml, go.mod, Cargo.toml, pyproject.toml, tsconfig.json, etc.) and src/ structure. Extract language, framework, ORM, testing, build tool, linter, commands, and project structure. Present findings and ask the user to confirm before proceeding.

  3. Copy template files — Copy only what's relevant to the selected tools:

    • Claude Code: CLAUDE.md, .claude/commands/coograph-*.md, .claude/hooks/ (all scripts), .claude/settings.json
    • VS Code Copilot: .github/agents/, AGENTS.md
    • Codex CLI, OpenCode, Cursor, Devin Desktop, Aider, Cline: per-tool files listed in SKILL.md § Step 3
    • Always (shared by every tool): .github/copilot-instructions.md, .github/instructions/, .github/skills/, openspec/config.yaml
    • Do NOT copy node_modules/, .omc/, or .claude/settings.local.json
    • Ask before overwriting any existing file (overwrite / skip / section-by-section)

  4. Fill placeholders — Replace all _TBD_ and <!-- FILL: ... --> markers using the detected stack info. Delete sections the user said to skip. Add project-specific rules.

  5. Verify — Grep for remaining _TBD_ or <!-- FILL markers. Ask the user for any still missing. Zero markers = done.

  6. Code-graph setup (if enabled) — See SKILL.md § Step 6 for the full procedure:

    • Copy .github/code-graph/ (exclude node_modules/)
    • Install d3: cd .github/code-graph && npm install
    • Ensure uv is available (install automatically if not)
    • Add .code-graph/ to .gitignore
    • Write MCP config(s) for selected tools
    • Build initial graph: uv run --with-requirements .github/code-graph/requirements.txt .github/code-graph/server.py --build
    • Optionally install git hooks for auto-updates

  7. Agent references (if code-graph enabled) — Verify every copied agent file still carries the MANDATORY — non-negotiable (or, under sync: em_dash: hyphen, MANDATORY - non-negotiable) Step 0 block; restore it verbatim from the template root where missing. See SKILL.md § Step 7.

  8. Register in projects.json (repo mode only — skipped for plugin installs) — Add the target project to projects.json in the coograph root (create with {"projects": []} if missing). Entry: { "path": "<absolute-path>", "tools": [...], "code_graph": true|false, "registered_at": "<date>" }. Then run ./setup.sh in the coograph root to ensure git hooks are configured for auto-sync on pull.

  9. Code-graph health check (if code-graph enabled) — Sanity-check node/edge/file counts in .code-graph/graph.db, report healthy or list issues, and offer a rebuild. See SKILL.md § Step 9.

  10. Retro first run, layout checks (if enabled) — SKILL.md § Steps 10 and 11.

  11. Doctor — run python3 .github/skills/coograph-doctor/doctor.py --project <target> last; every check PASS or SKIP (WARN only for a declined option). See SKILL.md § Step 12.

Read the full file on GitHub · 59 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. 11d ago Changed · +5 lines 3c80068d9e74
  2. 1mo ago Changed e594defce7e7
  3. 1mo ago Changed 01ddd0fdeb03
  4. 1mo ago Changed · +5 lines 3e3cc0dcafd8
  5. 2mo ago First seen · 49 lines · 0 tokens per session scan A 2799b3346ecb

Subscribe to this mod's changes

coograph-init is a command published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,136 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.

ai-agentsai-codingai-optimizationai-toolscode-graphtoken-ai-optimizator
Related

coograph-init compared with commands from other repositories

coograph-init next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
coograph-initpaullukic/coographCommand1712d agoMITA0Claude Code
pull-repostravisjneuman/.claudeCommand107yesterdayMITA13Claude Code
security-scantravisjneuman/.claudeCommand107yesterdayMITA6Claude Code
test-suitetravisjneuman/.claudeCommand107yesterdayMITA7Claude Code
standardize-claude-mdtravisjneuman/.claudeCommand107yesterdayMITA18Claude Code
helptravisjneuman/.claudeCommand107yesterdayMITA9Claude Code
api-genhalflength-ampleness75/claude-code-recipesCommand223d agoMITA14Claude Code