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/zevtos/agentpipe/onboardgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00031 | $0.00665 |
| Opus 5 | $0.00015 | $0.00332 |
| Sonnet 5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
onboard 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orienting yourself (and the user) to a project. Explore the codebase systematically and produce a clear mental map.
Context
@CLAUDE.md
Pipeline
Step 1: Project Identity
Gather basic facts:
- Read CLAUDE.md, README.md, and any project documentation
- Check package.json / pyproject.toml / Cargo.toml / go.mod for tech stack and dependencies
- Check git log for recent activity (last 20 commits)
- Check for CI/CD configuration (.github/workflows/, .gitlab-ci.yml, Jenkinsfile)
- Check for containerization (Dockerfile, docker-compose.yml)
Step 2: Architecture Map
Explore the codebase structure:
- List top-level directory structure
- Identify the main entry point(s)
- Map the module/package structure
- Identify external service integrations (APIs, databases, queues, caches)
- Identify the data model (ORM models, schema files, migrations)
- Identify the API surface (routes, controllers, handlers)
- Check for test structure and coverage approach
Step 3: Development Workflow
Identify:
- How to install dependencies
- How to run the project locally
- How to run tests
- How to build for production
- How to deploy
- Environment variables needed (.env.example)
- Git workflow (branching strategy, PR process)
Step 4: Current State
- Any open TODOs/FIXMEs in the code
- Dependency health (outdated packages, known vulnerabilities)
- Test suite status (run tests if possible)
- Recent changes (what's been worked on)
Step 5: Report
## Project Overview: [name]
### Tech Stack
- Language: [language + version]
- Framework: [framework + version]
- Database: [DB + version]
- Key dependencies: [list major deps]
### Architecture
[Brief description + Mermaid component diagram]
- Entry points: [main files]
- API layer: [where routes/handlers live]
- Business logic: [where domain logic lives]
- Data layer: [where DB access lives]
- External integrations: [services used]
### Directory Structure
[Annotated tree of key directories]
### Development Commands
| Action | Command |
|--------|---------|
| Install deps | `...` |
| Run dev server | `...` |
| Run tests | `...` |
| Build | `...` |
| Lint | `...` |
### Conventions
[Coding patterns, naming conventions, project-specific rules]
### Current State
- Last activity: [date + what was worked on]
- Test status: [passing/failing/unknown]
- Known issues: [TODOs, FIXMEs, outdated deps]
### Recommended First Steps
[What to do next based on the project state]
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.
- 2d ago First seen · 90 lines · 31 tokens per session scan A 7287822c668a
onboard is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 665 once invoked, about $0.0002 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 2026-08-30.
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.