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 skills add mir-am/skills-agents-ai-coding --skill gh-issue-fixgit clone --depth 1 https://github.com/mir-am/skills-agents-ai-codingWrote 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/skills/mir-am/skills-agents-ai-coding/gh-issue-fix)<a href="https://agentmods.dev/skills/mir-am/skills-agents-ai-coding/gh-issue-fix"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/gh-issue-fix/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/skills/mir-am/skills-agents-ai-coding/gh-issue-fix"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/gh-issue-fix.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 | $0.00028 | $0.01686 |
| Opus 5.5 | $0.00011 | $0.00674 |
| Sonnet 5.5 | $0.00006 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
gh-issue-fix 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 22d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
- Fetch an issue and investigate the relevant code
- Present a concise implementation plan and continue without waiting for approval
- Create or resume a dedicated issue branch
- Implement, test, and review the changes
- Use
git-commitandgh-prto commit, push, and open a linked PR - Verify the PR targets the default branch and closes the issue when merged
When to use me
Use when the user asks to fix or implement a GitHub issue by number or URL. The default outcome is a tested change published as a PR, with merging left as a separate action.
Honor a narrower user request, such as planning only or leaving changes uncommitted. Otherwise, invocation authorizes the issue-to-PR workflow without additional plan, commit, push, or PR confirmation prompts. Continue to respect tool permissions, branch protections, and execution-mode restrictions.
Phase 1: Issue Intake
- Use the supplied issue number or URL; ask for it only if missing.
- Check GitHub CLI access and identify the issue repository and its default branch. Resolve
<owner/repo>from the supplied URL, or from the current checkout for a bare issue number:
For an issue URL, resolve its repository explicitly and usegh auth status git remote -v gh repo view <owner/repo> --json nameWithOwner,defaultBranchRef gh issue view <number-or-url> --repo <owner/repo> --json number,url,title,body,labels,comments,assignees,state--repo <owner/repo>for subsequent GitHub commands. Confirm the working checkout belongs to that repository or its fork; do not apply the issue to an unrelated checkout. - Keep the issue number, URL, repository, and detected default branch available throughout the workflow. Do not assume the default branch is named
mainormaster. - Investigate unclear requirements in the code before asking questions. Ask only for missing information that prevents a correct implementation; choose reasonable defaults for routine decisions.
Phase 2: Exploration and Plan
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.
- 22d ago Changed · -59 lines · +5 tokens per session 071671d8d140
- 1mo ago First seen · 161 lines · 23 tokens per session scan A b5382add9d72
gh-issue-fix is a skill published in the GitHub repository mir-am/skills-agents-ai-coding (2 stars, last pushed 23d ago), licensed MIT. It adds 28 tokens to every session and 1,686 once invoked, about $0.0001 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 skills, from other repositories
beads
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or…
work
Pick up ready leaf yaks and implement them — dispatch subagents in isolated worktrees, then merge back to main.
packet-factory
Creates, reviews, and dispatches atomic work packets. Every task with a side effect requires an APPROVED packet before execution. Scope is immutable after approval — expansion requires a new packet.
file-todos
Manage file-based todos in todos/ directory. Use when creating, triaging, or tracking todos and integrating them with code review.
lavra-work
Execute work on one or many beads -- auto-routes between single-bead, sequential, and multi-bead parallel paths based on input.
yak-worktree-workflow
Use when starting work on a yak - sets up an isolated git worktree, reads yak context, and guides the full cycle from claiming through merge and cleanup.