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-gh-assign)<a href="https://agentmods.dev/commands/leanandmean/scramjet/mach12-gh-assign"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-gh-assign/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-gh-assign"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/mach12-gh-assign.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 | $0.00017 | $0.00695 |
| Opus 5 | $0.00009 | $0.00347 |
| Sonnet 5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
mach12:gh-assign 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assign GitHub Issues
Goals
- Give every requested issue an explicit assignment resolution while preserving existing assignees unless the user chooses otherwise.
- Return a caller-consumable per-issue resolution summary.
This subroutine is gh-specific. A future forge-agnostic command set would substitute an equivalent glab-assign (or similar); the three-way decision logic stays the same.
Assignment failures are non-blocking. Warn the user in CLI output and continue -- a failed assignment must not block the caller's workflow.
Step 1: Parse input
Extract one or more issue numbers (space-separated). If no issue numbers are present, return an error to the caller and stop.
Step 2: Resolve the current user
gh api user --jq .login
Record the login. If the call fails, warn the caller and stop -- the assignment cannot proceed without a target user.
Step 3: Classify each issue
For each issue number, read its current assignees:
gh issue view <issue-number> --json assignees --jq '[.assignees[].login] | join(",")'
Classify each issue into one of three buckets:
- Already assigned to the current user: skip silently (the user need not be told). This is the expected case when returning for subsequent stages.
- No assignees: auto-assign immediately with
gh issue edit <issue-number> --add-assignee @me. Record the success or failure. - Other assignees (not including the current user): collect into a conflicting list along with the existing assignees.
Step 4: Resolve conflicts
If the conflicting list is empty, skip to Step 5.
If the conflicting list has one or more entries, present a single bulk decision prompt to the user. The same choice applies to every conflicting issue -- callers that pass a parent and its sub-issues in one invocation get one prompt covering all of them, by design. Per-issue decisions are not supported; if a caller needs them, it should call the subroutine separately for each issue.
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 Changed · +3 lines 103bf91e7144
- 8d ago First seen · 64 lines · 17 tokens per session scan A 065f9565fa33
mach12:gh-assign is a command published in the GitHub repository LeanAndMean/scramjet (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 695 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
computer
Drive a computer's screen, mouse, and keyboard.
find-issues
Find GitHub issues that a PR might fix.
afc
Create feature - creates spec in inbox (shortcut for feature-create).
afcl
Close feature [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers (shortcut for feature-close).
afd
Do feature - works in both Drive and Fleet modes (shortcut for feature-do).
next
Suggest the most likely next workflow action based on current context.