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 hmj1026/dhpk --skill create-prgit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/hmj1026/dhpk/create-pr)<a href="https://agentmods.dev/skills/hmj1026/dhpk/create-pr"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/create-pr/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/hmj1026/dhpk/create-pr"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/create-pr.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 | $0.00059 | $0.00791 |
| Opus 5.5 | $0.00024 | $0.00316 |
| Sonnet 5.5 | $0.00012 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
create-pr 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR
Workflow
Run in the consumer repository and preserve the supplied arguments. Resolve
--head to the current branch and --base to {TARGET_BRANCH} or main
when they are omitted. Gather the branch, remote, existing PRs, recent
commits, and diff statistics before composing the request.
Extract a ticket from the branch with {TICKET_PATTERN} (default
[A-Z]+-\d+), then generate <type>: [<TICKET>] <summary> unless
--title overrides it. Build the body from a concise summary, the ticket link
when resolved, and verification evidence. Separate checks actually run from
planned checks marked NOT RUN; for behavior changes, include a compact
before/after example or evidence. Label an unobserved after-state as expected
and list its check as NOT RUN. Add rollback and blast-radius details when
they materially affect review. Use a visual aid only when it clarifies the
change; do not include one by default. Before any PR creation, run the
pre-flight checks in
references/workflow.md, including
git rev-list --count <base>..HEAD. A zero count stops with the exact message
No commits between <base> and HEAD — nothing to open a PR for.
Dry-run is the default and only prints a copy-pasteable gh pr create
command. --execute is the sole creation path: verify the branch is pushed,
verify no PR already exists, require the existing GitHub authorization, ask
for confirmation, and then report the URL. Do not push or create commits.
When NOT to Use
- The branch still needs commits or a push.
- An existing PR must be edited, merged, or closed.
- A release, tag, or deployment is the requested operation.
Output
- Dry-run: one copy-pasteable
gh pr createcommand block and no PR URL claim. - Execute: the URL returned by
gh pr create. - Missing refs, no commits, an unpushed branch, an existing PR, unavailable
gh, failed authorization, or failed confirmation are terminal failures; never report a created PR without the URL evidence.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 222 B
- distribution.yaml 2.7 KB
- references/merge-prep/agents/openai.yaml 185 B
- references/merge-prep/distribution.yaml 2.1 KB
- references/merge-prep/references/workflow.md 1.4 KB
- references/merge-prep/SKILL.md 2.3 KB
- references/pr-summary/agents/openai.yaml 189 B
- references/pr-summary/distribution.yaml 2.0 KB
- references/pr-summary/references/workflow.md 1.5 KB
- references/pr-summary/SKILL.md 2.1 KB
- references/workflow.md 2.3 KB
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 · +8 lines 98a64821f3cd
- 10d ago Changed · +9 lines 7e6f8f2ecb80
- 23d ago First seen · 57 lines · 59 tokens per session scan A 68a3366d3f1a
create-pr is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 791 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
avatar-contribution-pr
Turn an avatar GitHub issue (from the in-app avatar-editor easter egg) into a merged sprite — validate the art, then either add a new module or replace an existing one, and open a PR that closes the issue. Handles both "Avatar contribution: " (a brand-new sprite) and "Avatar edit: " (a hand-redraw of an existing…
release
Release a new version of the mumei repository. Invoke when the user gives an explicit release instruction ("release it", "/release", "patch release", "ship 0.2.0"). Takes no argument or "patch" / "minor" / "major" for a SemVer bump, or a direct version such as "0.2.0". Wraps any uncommitted changes into a single…
generator-fix-integrator
Internal Auto-Harness generator skill for worktree-merge fix integration. Use only inside the parallel Generator integrator when it is addressing named defects from QA or retest.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
update-pr
Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest commits. Triggers on: update pr, update-pr, update the pr, push to pr, refresh pr, sync pr, update pull request.
merge-prep
Pre-merge analysis and preparation. Analyzes source branch vs target branch: commit stats, conflict detection, file impact. Analysis-only v1 — outputs report + suggested commands, does not auto-merge. Use when: user says 'merge prep', 'pre-merge', 'merge analysis', or /merge-prep.