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 alunduil/alunduil-chezmoi --skill issue-creategit clone --depth 1 https://github.com/alunduil/alunduil-chezmoiWrote 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/alunduil/alunduil-chezmoi/issue-create)<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/issue-create"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/issue-create/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/alunduil/alunduil-chezmoi/issue-create"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/issue-create.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 | $0.00067 | $0.00904 |
| Opus 5 | $0.00034 | $0.00452 |
| Sonnet 5 | $0.00013 | $0.00181 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
issue-create 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 11d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue create
Don't file first. Search and inspect before composing.
Dedup pre-flight
Open and closed — omitting --state searches both:
gh search issues "<keywords>" --repo <owner>/<repo> --limit 20
Read near-matches with gh api repos/:owner/:repo/issues/<N>. Decide:
- Same outcome already open — update the existing one
(
mcp__github__issue_writewithmethod: updatefor the body,mcp__github__add_issue_commentfor new context). Don't file a new one. - Same outcome closed for stale reasons — reopen it
(
mcp__github__issue_write,method: update,state: open) with a comment citing what changed. Don't file a new one. - Adjacent (same area, different angle) — file new, cite the
existing in Additional context; consider an
issue-linksedge. - Partially covers — narrow the new issue to the uncovered slice; cross-reference both ways.
- Nothing close — file new.
If torn, surface the call rather than silently pick.
Detect repo conventions
ls .github/ISSUE_TEMPLATE/ 2>/dev/null
# REST reads — see ~/.claude/CLAUDE.md "GitHub API budget".
gh api 'repos/:owner/:repo/labels?per_page=100' --jq '.[].name'
gh api repos/:owner/:repo/milestones \
--jq '.[] | "\(.number)\t\(.title)"' # open only — can't assign a closed one
gh api 'repos/:owner/:repo/issues?per_page=5&state=all' \
--jq '.[].title' # skim recent house style
Template present → read it and fill its fields into the body. Templates encode the project's required fields; don't bypass with a freeform body.
Standard structure (no template)
- Title — statement true when done. Active voice, outcome. "Profile writes persist across API restarts in Firestore", not "Fix profile persistence".
- Summary — 1-2 sentences. What this delivers.
- Motivation — what problem, dependency, or opportunity drives it. Cite the trigger (PR review, incident, related issue).
- Scope — concrete changes, specific enough to start without guessing. Bullets, not prose.
- Acceptance criteria — measurable conditions,
- [ ]task-list. - Additional context — links, screenshots, related issues, only when they help. Skip the section if empty.
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.
- 11d ago First seen · 94 lines · 67 tokens per session scan A aa76f878af42
issue-create is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 67 tokens to every session and 904 once invoked, about $0.0003 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 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.
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
project-backlog
Turn audit findings into deduplicated, prioritized issue drafts with dependencies and explicit authorization before GitHub mutation.
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.
create-pr
Create a pull request with auto-generated description, issue linking, ROADMAP updates, and PR-metadata validation.