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-issue-create)<a href="https://agentmods.dev/commands/leanandmean/scramjet/mach12-issue-create"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-issue-create/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-issue-create"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-issue-create.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 | $0.00011 | $0.04689 |
| Opus 5.5 | $0.00004 | $0.01876 |
| Sonnet 5.5 | $0.00002 | $0.00938 |
| Haiku 4.5 | $0.00001 | $0.00469 |
Grade C, and why
mach12:issue-create scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "$duplicate_search_dir"' EXIT How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Issue
Goals
- Capture the user's supported problem, constraints, evidence—including material active-session evidence a future session cannot reasonably reconstruct—and observable desired outcome in one accurate, implementation-neutral issue artifact.
- Publish only a complete, internally reviewed issue or selected related-context comment through the guarded approval and exact-verification boundary.
- Apply requested or repository-standard metadata only after verified issue creation, and report each outcome without recreating the issue.
- When an artifact is published, return its verified repository-qualified identity; offer planning only when a newly created issue in the checkout repository is ready.
Step 1: Identify the problem
Use evidence in this order:
- descriptive content supplied with the command.
- A structured artifact explicitly supplied or adopted by the user.
- The immediate session context and recent conversation that led to this invocation, including an encountered bug, requested capability, deferred finding, confusing workflow, or unresolved concern.
- Relevant recent repository observations already established in the active session.
Within this authority order, prioritize material evidence that a future session could not reasonably reconstruct, especially evidence accumulated before a mid-session invocation. Preserve detail in proportion to reconstruction difficulty; reacquire readily available repository facts from their authoritative source instead of transporting redundant session copies.
Preserve user intent, experienced symptoms, constraints and non-goals, clarification answers, and other session-only problem evidence as attributed evidence, including when that evidence also contains objectively checkable factual premises. Preserve the attribution while separately verifying only any checkable premise whose falsity would materially change the problem identity, actual behavior, impact, proposed outcome, or acceptance criteria. Treat implementation preferences as preferences or explicit constraints, not as contradictions that must be resolved during issue creation.
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.
- 20d ago Changed · -10 lines 451cb948120a
- 1mo ago Changed · +2 lines 12857c996353
- 1mo ago Changed · +9 lines fed7b17870ef
- 1mo ago First seen · 242 lines · 11 tokens per session scan C 2dae2a737728
mach12:issue-create is a command published in the GitHub repository LeanAndMean/scramjet (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 11 tokens to every session and 4,689 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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).