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/leanandmean/scramjet/mach12-issue-implementgit clone --depth 1 https://github.com/LeanAndMean/scramjetWhat 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 | $0.00010 | $0.02906 |
| Opus 5 | $0.00005 | $0.01453 |
| Sonnet 5 | $0.00002 | $0.00581 |
| Haiku 4.5 | $0.00001 | $0.00291 |
Grade A, and why
mach12:issue-implement 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 3d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Stage
You are implementing a specific stage of a staged implementation plan. This command gathers context from a GitHub issue, then walks through the implementation under the structured development workflow.
Step 1: Parse Input
The user's input typically contains:
- An issue number (required)
- A stage number or range (required)
- Additional context or constraints (optional)
Example inputs:
55 155 2 but only the frontend parts55 stages 3-4
Extract the issue number and stage(s). If the input is ambiguous, ask the user to clarify.
Step 2: Ensure Feature Branch
Before gathering context or doing any work, ensure you are on an appropriate feature branch. Implementation must never happen directly on the default branch.
Determine the current branch and the default branch:
git branch --show-current
gh repo view --json defaultBranchRef --jq .defaultBranchRef.name
If on the default branch
-
Check for uncommitted changes with
git status --porcelain. If the working tree is dirty, stop and tell the user to commit or stash their changes before proceeding. -
Search for convention-named branches that match the issue number. Run
git branch -aand normalize each result by trimming leading whitespace and stripping theremotes/origin/prefix if present. Then filter for branches that start withfeature/issue-<number>-orfix/issue-<number>-, or that equalfeature/issue-<number>orfix/issue-<number>exactly. Use strict matching so thatissue-4-does not matchissue-42-. -
Exactly one match found: Check it out with
git checkout <branch>andgit pull --ff-only. If the pull fails because local and remote have diverged, stop and tell the user to resolve the divergence before continuing. -
Multiple matches found: Present the list to the user and ask them to choose. Use the branch names as option labels (if more than 4 branches match, list the 4 most recently updated; let the user supply another value if none fit).
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.
- 3d ago First seen · 177 lines · 10 tokens per session scan A 15193c622306
mach12:issue-implement is a command published in the GitHub repository LeanAndMean/scramjet (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 10 tokens to every session and 2,906 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
project_init
이 프로젝트를 ocul-pm 추적 대상으로 초기화 (.oculpm/ + 기록 규칙 생성) — 사용자가 직접 실행하는 명시적 시작.
inception
새 프로젝트/기능 영역의 설계 시작 — 리서치→사양 확정→3-depth 계획→EVALS→rules 시드.
next
활성 플랜의 다음 미완 리프를 잡아 구현 — 구현→검증→일지→플랜 갱신 한 사이클.
standup
ocul-pm 추적 프로젝트의 오늘 작업 스탠드업 — 일지·플랜 진행을 모아 요약 보고.
capture
Record what this session learned so a future session in a related repository can find it.
lens
Review a prompt, page, component, or draft through expert lenses (findings), fix it in place with --fix, or grade a prompt against a rubric with --grade (verdict + --against comparison).