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 pr-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/pr-create)<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/pr-create"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/pr-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/pr-create"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/pr-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 | $0.00085 | $0.01352 |
| Opus 5.5 | $0.00034 | $0.00541 |
| Sonnet 5.5 | $0.00017 | $0.00270 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
pr-create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR create
Compose before opening. The body is the squash-merge commit
context — write it for the reviewer first, the future reader of
git log second.
Pre-flight
# REST reads — see ~/.claude/CLAUDE.md "GitHub API budget".
branch=$(git branch --show-current)
gh api repos/:owner/:repo/pulls \
--jq ".[] | select(.head.ref==\"$branch\") | {number, state, url}" # existing PR for this branch?
git log --oneline main..HEAD # what this PR actually contains
gh api repos/:owner/:repo/pulls/<N> --jq '.body' # iterating? read the current body
- Existing PR for the branch → iterate on it, don't open a second.
- Find the issue this resolves (branch name, commit trailers, the
task). A PR that closes one carries
Closes #<N>in the body.
Detect repo template
ls .github/pull_request_template.md \
.github/PULL_REQUEST_TEMPLATE.md \
.github/PULL_REQUEST_TEMPLATE/ \
docs/pull_request_template.md 2>/dev/null
Template present → fill its sections; don't swap its structure for ours. Absent → use the structure below.
Body structure (no template)
Three short blocks. A reviewer should grasp all three in one read; a block that runs past a few lines is carrying detail the diff already shows.
- Summary — why this change. Prose, 1-2 sentences leading with
the user-visible outcome ("X now works"), not the diff ("set Y to
Z"). Surface mechanism only when the choice isn't obvious. Link the
issue; don't re-explain it.
Bad: "Set
format_space \"#[bg=16]\"in pair.kdl." Good: "Bar paints uniformly black across the format gap, closing the lighter strip from #68." - Gotchas — what'll surprise the reviewer. A bullet per pointer:
where to spend attention and why, not an exhaustive risk dump.
Typical: off-diff state (a label/secret/setting changed remotely), a
silent-failure mode, a non-obvious constraint, something that reads
like a typo. Litmus: a gotcha completes "watch out —
___", not "I chose___because___"; rationale goes to Summary or gets cut. Omit when nothing surprises. Bad: "Split into two workflows so each trigger is self-documenting." Good: "Labeling pins.../autolabeler@<sha>, a subpath of the same action — not a typo." - Verification — how we know it's correct. A bullet per material check beyond CI, past tense ("ran X, confirmed Y"). Skip trivial steps. Omit the section when CI covers everything; unverified items go in Gotchas, not here.
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.
- yesterday Changed · +4 lines 7cc671a54ff1
- 1mo ago First seen · 132 lines · 85 tokens per session scan A e55f8e1f638b
pr-create is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 85 tokens to every session and 1,352 once invoked, about $0.0003 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
github-pull-request
Open, update, verify, and merge GitHub pull requests.
merge-ready
Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…
pr
Prepare, push, and open a GitHub pull request for a Jujutsu (jj) revision. Use only when asked to create or open a PR; do not use for ordinary review or local commits.
gh-pr
This skill should be used when creating a GitHub pull request via gh pr create. Covers the gh CLI mechanics; PR title and body conventions come from the pr-style skill.
dr-review
Review the local diff against Darkroom's checklist, or address feedback on the active PR. Triggers "review my changes", "check this diff", "address PR feedback". Native /code-review handles a diff or PR without the checklist.
pr-grooming
Use when the user wants to groom, triage, or clean up the open pull requests of a repo: "groom the PRs", "review the open PRs", "which drafts are stale", "close old draft PRs", "rebase the dependabot PRs", "are the open PRs still mergeable", "refresh that old bugfix PR", or a periodic PR review — even when they do not…