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/marmot-protocol/agent-configWrote 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/marmot-protocol/agent-config/fix-gh-issue)<a href="https://agentmods.dev/commands/marmot-protocol/agent-config/fix-gh-issue"><img src="https://agentmods.dev/badge/commands/marmot-protocol/agent-config/fix-gh-issue/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/marmot-protocol/agent-config/fix-gh-issue"><img src="https://agentmods.dev/badge/commands/marmot-protocol/agent-config/fix-gh-issue.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 | $0.00008 | $0.00529 |
| Opus 5.5 | $0.00003 | $0.00212 |
| Sonnet 5.5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
fix-gh-issue 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.
What it actually says
Fix GitHub Issue
Verify an issue from GitHub is valid, create a worktree to work on it, fix the issue, and create a PR.
Instructions
1. Parse and Validate Arguments
- Read ISSUE_NUMBER from $ARGUMENTS
- Accept: bare number (
5), issue number (#5), or full URL (https://github.com/org/repo/issues/5) - Extract just the number. If parsing fails, report an error and stop.
2. Validate Issue
- Fetch the issue using
gh issue view <ISSUE_NUMBER> - Read any files in the codebase related to the issue to understand context
- Determine if this is a valid problem, feature, or task worth working on
- If not valid, explain why and stop
- If valid, continue
3. Create Worktree
- Create a short ISSUE_DESCRIPTION from the issue title (lowercase, hyphens, no special chars)
- Set BRANCH_NAME to
issue-<ISSUE_NUMBER>-<ISSUE_DESCRIPTION> - Run:
/create-git-worktree <BRANCH_NAME> - You are now in the worktree directory, ready to work
4. Fix the Issue
- Implement the fix or feature
- Run quality checks:
just precommitorjust ci - Check code coverage:
just coverage-text- All quality checks must pass
- Code coverage must be equal or greater than HEAD
- If checks fail, fix issues and re-run until passing
5. Create PR
- Commit changes with a descriptive message
- Create a PR:
gh pr create --fill - Include
Closes #<ISSUE_NUMBER>in the PR body
7. Run code-review
- Once you've published a PR, start a new session with the /new command
- Then run the /code-review command to do a full code review.
- If any issues are surfaced, fix them, run all code quality checks again, and then commit and push your changes
7. Report
After successful PR creation, provide this report:
✅ Issue #<ISSUE_NUMBER> Successfully Completed!
📁 Worktree:
Location: trees/<BRANCH_NAME>
Branch: <BRANCH_NAME>
🔗 GitHub:
Issue: <FULL_ISSUE_URL>
PR: <FULL_PR_URL>
📝 Summary:
<Summary of changes made>
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 First seen · 72 lines · 8 tokens per session scan A 658df2ce2049
fix-gh-issue is a command published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 529 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
barista-fix
Attempt a small, focused fix for a frappe-ui issue and open a draft PR.
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…
unbloat
Remove dead code, duplicate files, and unused dependencies with user approval at each step. Backs up before deleting.
payload-revert
Stage reverts for high-confidence payload candidates identified by payload-analysis.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.
fix-issue
Analyze and fix the GitHub issue: $ARGUMENTS.