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/kickoffgit 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 | $0.00840 |
| Opus 5 | $0.00015 | $0.00420 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
kickoff 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a full project kickoff. The user has an idea and wants a production-ready project foundation. Follow this pipeline EXACTLY, step by step. Do NOT skip steps. Do NOT implement code until all planning agents have completed.
Context
@CLAUDE.md
The Idea
$ARGUMENTS
Pipeline
Step 1: Requirements (PM Agent)
Run the pm agent with this prompt:
"The user wants to build: $ARGUMENTS
Create a comprehensive product specification including:
- Problem statement and target users
- Core user stories with acceptance criteria (Given/When/Then)
- Feature list prioritized as Must/Should/Could/Won't (MoSCoW)
- Non-functional requirements (performance targets, security requirements, scalability)
- Edge cases and error scenarios
- Open questions that need answers
- Success metrics"
Present the PM output to the user. Ask: "Does this spec capture what you want? Any changes or missing requirements?" Wait for user confirmation before proceeding.
Step 2: Architecture (Architect Agent)
Run the architect agent, passing the confirmed spec:
"Based on this product specification:
[paste confirmed PM output]
Design the system architecture:
- Technology stack selection with ADRs for each major choice
- System decomposition (bounded contexts, service boundaries)
- API contract design (endpoints, request/response shapes, error handling)
- Data model (entities, relationships, constraints)
- Component diagram (Mermaid)
- Integration patterns (sync/async, queues, external services)
- Infrastructure requirements
- Evolution path for future scaling"
Present the architecture to the user. Ask: "Does this architecture work for you? Any technology preferences or constraints I should adjust?" Wait for user confirmation before proceeding.
Step 3: Database Design (DBA Agent)
Run the dba agent, passing the architecture:
"Based on this system architecture:
[paste confirmed architect output — specifically the data model section]
Design the complete database schema:
- Table definitions with exact types, constraints, and indexes
- Migration files for initial schema setup
- Seed data if applicable
- Index strategy for expected query patterns
- Backup strategy recommendation
- ER diagram (Mermaid)"
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 · 97 lines · 31 tokens per session scan A c1a0ebb098ea
kickoff 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 840 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.