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.
git clone --depth 1 https://github.com/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/mach12-plan-comment-contract)<a href="https://agentmods.dev/commands/leanandmean/scramjet/mach12-plan-comment-contract"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-plan-comment-contract/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.
<a href="https://agentmods.dev/commands/leanandmean/scramjet/mach12-plan-comment-contract"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-plan-comment-contract.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00010 | $0.01485 |
| Opus 5.5 | $0.00004 | $0.00594 |
| Sonnet 5.5 | $0.00002 | $0.00297 |
| Haiku 4.5 | $0.00001 | $0.00148 |
Grade A, and why
mach12:plan-comment-contract 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Comment Contract
Goals
- Make the caller-owned implementation plan a complete, standalone, post-ready artifact that a fresh implementation session can execute.
- Preserve implementation-critical contracts, decisions, and provenance while removing duplicate or non-actionable planning material.
- Return unresolved evidence gaps instead of allowing an incomplete plan to carry the publication marker.
Delegation loads this policy into the caller's current model context; it does not execute an independent formatter or return a separately generated plan.
Step 1: Select the mode
Accept exactly one mode:
initial— shape the first durable implementation plan from the caller's planning evidence and user decisions.revision— shape a complete replacement from the prior plan, classified review deltas, architect evidence, pitfalls, and decisions.
If the mode is absent or invalid, state that the contract cannot be applied and stop. Do not infer a mode.
Step 2: Build one standalone artifact
Resume the caller-owned drafting or revision work under this contract. The result must be the exact post-ready Markdown
body, with <!-- mach12-plan --> as its first line. Only a complete body that has passed Step 6 may carry that marker.
Make the artifact independently usable by an implementation agent in a fresh session. It must state the goal and scope, the selected design and concise rationale, a test strategy proportionate to the change, session-sized implementation stages, actionable pitfalls, and a decision log when meaningful decisions exist.
Give each substantive requirement one authoritative home, normally the stage that implements it. Each stage must identify its outcome, files to create or modify, implementation-critical contracts, dependencies, and verification. Overview, test, pitfall, and decision sections may summarize or cross-reference stage content but must not repeat complete stage instructions or duplicate test matrices.
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.
- 1mo ago Changed · +1 lines 861ce6fdc128
- 1mo ago Changed · +2 lines 7f7c883dec65
- 1mo ago Changed · +5 lines e4b94384952d
- 1mo ago First seen · 128 lines · 10 tokens per session scan A 9606fa56de4f
mach12:plan-comment-contract is a command published in the GitHub repository LeanAndMean/scramjet (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,485 once invoked, about $0.0000 per session on Opus 5.5. 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
afcl
Close feature [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers (shortcut for feature-close).
next
Suggest the most likely next workflow action based on current context.
aft
Transfer feature from its current agent to a different agent — preserves commits and in-flight work (shortcut for feature-transfer).
aigon-feature-transfer
Hand a stuck or paywalled in-progress feature from its current agent to a different agent, without losing commits or in-flight work. Intended for.
afs
Start feature [agents...] - create workspace and begin implementation (shortcut for feature-start).
afo
Open feature worktree in terminal and start agent (shortcut for feature-open).