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 fmind/dotfiles --skill github-issuesgit clone --depth 1 https://github.com/fmind/dotfilesWrote 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/fmind/dotfiles/github-issues)<a href="https://agentmods.dev/skills/fmind/dotfiles/github-issues"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/github-issues/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/fmind/dotfiles/github-issues"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/github-issues.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 | $0.00036 | $0.00614 |
| Opus 5.5 | $0.00014 | $0.00246 |
| Sonnet 5.5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
github-issues 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage GitHub Issues
Use gh for evidence-backed issue operations. project-backlog owns local issue drafts; this skill owns confirmed remote issue state and authorized mutation.
Workflow
-
Confirm the target: Resolve the repository from the explicit URL or
git remote get-url origin, then stateOWNER/REPO. Never infer a different repository from a similarly named checkout. -
Refresh current state: Read the issue and relevant neighbors before proposing a change:
gh issue view <number> -R <owner>/<repo> --json number,title,body,state,stateReason,labels,assignees,milestone,comments,url gh issue list -R <owner>/<repo> --state all --search '<distinct terms>' --json number,title,state,url -
Deduplicate and preserve evidence: Prefer updating an existing issue when it represents the same outcome. Keep reproduction, acceptance criteria, dependencies, decisions, and proof; remove stale activity logs and duplicate checklists.
-
Check authority: Reading and drafting are safe defaults. Creation, edits, labels, assignments, comments, closure, reopening, locking, transfer, project changes, and deletion are separate remote mutations requiring user authority.
-
Apply one bounded mutation: Prepare substantial bodies in a temporary file and pass it with
--body-file; avoid shell interpolation and interactive prompts:gh issue create -R <owner>/<repo> --title '<title>' --body-file <body-file> gh issue edit <number> -R <owner>/<repo> --body-file <body-file> -
Verify from GitHub: Re-read the issue with
gh issue view --json ..., compare the intended fields, and report its URL. A successful command alone is not proof of final state.
Boundaries
- Do not close an issue merely because local code is green; verify the issue's acceptance criteria and requested delivery boundary.
- Do not assign people, notify them in comments, or alter projects and milestones without explicit coordination authority.
- Do not create issues from raw review findings until project-backlog has deduplicated and prioritized them.
- Use plan-execution for implementing an accepted issue and github-pull-request for the resulting PR.
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 · 43 lines · 36 tokens per session scan A 7b7e55e5bb9b
github-issues is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 614 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
work-on
End-to-end workflow for shipping a GitHub issue. Assesses complexity, builds a tailored workflow, and orchestrates skills from research through PR.
resolve-conflicts
Resolve Git merge or rebase conflicts by both sides' intent; verify the result.
github-repository
Set GitHub repo description, topics, merge policy, and security settings.
acli
Search, plan, and update Atlassian Jira and Confluence with acli.
github-issues
Plan, draft, update, link, and close GitHub issues.
github-pull-request
Open, update, and verify GitHub pull requests.