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/racecraft-lab/racecraft-plugins-public/commitgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWhat 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 | $0.00011 | $0.00499 |
| Opus 5 | $0.00005 | $0.00249 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
Checkpoint Commit 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.
This is a copy
92% identical to Checkpoint Commit — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
/speckit.checkpoint.commit
Description
Stages all current changes and creates a commit with a descriptive message reflecting the work just completed. This command should be called by the agent at two points during the spec-kit workflow:
- After each pre-implementation step (constitution, specify, clarify, plan, analyze, tasks) — to capture the spec artifacts produced by that step.
- During implementation — at natural checkpoints, such as after completing a task or a logical group of related tasks from the task list.
When to Commit
Pre-Implementation Steps
Commit immediately after each of these steps completes:
- After constitution — commit the project principles and guidelines
- After specify — commit the requirements and user stories
- After clarify — commit the resolved clarifications
- After plan — commit the technical implementation plan
- After analyze — commit the consistency and coverage analysis
- After tasks — commit the task breakdown
During Implementation
Use the task list generated during the tasks step as a reference for when to commit. Good checkpoints include:
- Completing a single task from the task list
- Completing a logical group of closely related tasks
- Finishing a self-contained unit of work (e.g., a new component, a service layer, a set of tests)
The agent should use judgment — the goal is to produce commits that are meaningful and reviewable, not to commit after every single file change.
Workflow
- Determine a clear, concise commit message based on the work just completed
- Stage all current changes (
git add -A) - Commit with the message (
git commit -m "<message>")
Commit Message Guidelines
- For pre-implementation steps, use the step name as a prefix (e.g.,
constitution: establish project principles,tasks: break down implementation into actionable items) - For implementation commits, describe what was built (e.g.,
implement user authentication service,add product listing page and API routes) - Keep messages concise but descriptive enough to understand the scope of the commit
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 · 56 lines · 11 tokens per session scan A 5261cd7c0c01
Checkpoint Commit is a command published in the GitHub repository racecraft-lab/racecraft-plugins-public (4 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 499 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to Checkpoint Commit, differing in 10 lines, and is treated as a copy.
Other commands, from other repositories
build
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
deepen
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
research
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.
review
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
spec
Create, amend, or backprop bug into SPEC.md. Sole mutator of spec.
check
Drift detector. Diff SPEC.md against code. Read-only, zero writes.