mach12:issue-create

mach12:issue-create is a command for coding agents from LeanAndMean/scramjet. It costs 11 tokens per session (3,768 once invoked), scanned C, original, Apache-2.0.

A command that turns a reported problem into a structured GitHub issue, a tracked record of a bug, request, or concern.

In plain words
What is it for?
Use it to record bugs, requested capabilities, confusing workflows, deferred review findings, or unresolved concerns after confirming the issue details.
Why use it?
It preserves the user’s symptoms, constraints, and context while separating those reports from facts that still need verification.

Command

Install

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.

agentmods
npx agentmods add commands/leanandmean/scramjet/mach12-issue-create
Clone the repo
git clone --depth 1 https://github.com/LeanAndMean/scramjet

Wrote 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.

agentmods badge for mach12:issue-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-issue-create.svg)](https://agentmods.dev/commands/leanandmean/scramjet/mach12-issue-create)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.03768
Opus 5 $0.00005 $0.01884
Sonnet 5 $0.00002 $0.00754
Haiku 4.5 $0.00001 $0.00377

Measured 4d ago against content hash 2dae2a737728, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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
packages/scramjet/mach12/commands/mach12:issue-create.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Issue

You are identifying and accurately capturing the problem that motivated this command, then creating a structured GitHub issue after explicit user approval.

Step 1: Identify the problem

Use evidence in this order:

  1. descriptive content supplied with the command.
  2. A structured artifact explicitly supplied or adopted by the user.
  3. 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.
  4. Relevant recent repository observations already established in the active session.

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.

Do not search historical sessions merely because the command has no descriptive argument. Use the general prior-session fallback only when current evidence points to relevant earlier work and the missing detail matters.

Classify the evidence as one clear candidate problem, multiple distinct candidate problems, or no supported candidate:

  • If one candidate is clear, proceed without asking the user to repeat evident context.
  • If one candidate is plausible but uncertain, state what likely prompted the command and ask for confirmation or correction.
  • If multiple distinct candidates are supported, ask which one should become the issue and do not silently combine unrelated problems. A tracking issue or multiple issues requires explicit user direction.
  • If no supported candidate is clear, ask what problem, missing capability, or concern the user wants captured.

Read the full file on GitHub · 242 lines

Changes

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.

  1. 4d ago First seen · 242 lines · 11 tokens per session scan C 2dae2a737728

Subscribe to this mod's changes

mach12:issue-create is a command published in the GitHub repository LeanAndMean/scramjet (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 11 tokens to every session and 3,768 once invoked, about $0.0001 per session on Opus 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.