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 commands/terrene-foundation/metis/startgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/commands/terrene-foundation/metis/start)<a href="https://agentmods.dev/commands/terrene-foundation/metis/start"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/start.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 | $0.00016 | $0.00721 |
| Opus 5 | $0.00008 | $0.00360 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
start 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Present this orientation to the user in a warm, clear, jargon-free way. Adapt tone based on context — if they seem technical, be concise; if they seem new, take more time.
What is COC?
COC is a structured workflow where YOU direct an AI to build software. You don't need to write code. Your job is to:
- Describe what you want (in your own words, as detailed as you like)
- Make decisions when choices come up (we'll always explain the options clearly)
- Approve the plan before building starts
- Review the results to make sure they match your vision
The AI handles all the technical work — writing code, testing, security checks, and deployment.
The 5 Phases
| Step | Command | What Happens | Your Role |
|---|---|---|---|
| 1. Research | /analyze |
Study your idea — market fit, user needs, competition | Confirm we understood your vision |
| 2. Planning | /todos |
Create a complete project roadmap | Approve the plan before building starts |
| 3. Building | /implement |
Build the project one task at a time | Answer questions when choices come up |
| 4. Testing | /redteam |
Test everything from a real user's perspective | Review results |
| 5. Knowledge | /codify |
Capture what we learned for future sessions | Confirm the knowledge is accurate |
Plus /deploy when you're ready to launch, and /ws anytime to check progress.
Getting Started
Walk the user through these steps:
- Create a workspace: Ask the AI to set up a workspace for your project (e.g., "create a workspace called my-project"), or manually create a folder
workspaces/my-project/briefs/ - Write a brief: Create a file in the briefs folder describing what you want to build — in your own words, as detailed as you like. Include who it's for, what problem it solves, and what success looks like. You can also just tell the AI what you want and ask it to write the brief for you.
- Run
/analyze: This kicks off the research phase
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.
- 3d ago First seen · 56 lines · 16 tokens per session scan A db1d4d1c6aca
start is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 721 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.