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 willvelida/code-minions --skill raise-pull-requestsgit clone --depth 1 https://github.com/willvelida/code-minionsWrote 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/willvelida/code-minions/raise-pull-requests)<a href="https://agentmods.dev/skills/willvelida/code-minions/raise-pull-requests"><img src="https://agentmods.dev/badge/skills/willvelida/code-minions/raise-pull-requests/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/willvelida/code-minions/raise-pull-requests"><img src="https://agentmods.dev/badge/skills/willvelida/code-minions/raise-pull-requests.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 | $0.00082 | $0.00876 |
| Opus 5.5 | $0.00033 | $0.00350 |
| Sonnet 5.5 | $0.00016 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
raise-pull-requests 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raise Pull Requests
Overview
A skill for raising pull requests that are easy to review, clearly described, and follow team conventions. Good pull requests reduce review time, catch bugs earlier, and keep the team informed about what is changing and why.
This skill covers the full lifecycle of a pull request — from preparing your changes through responding to review feedback.
Principles
1. Write Small, Focused Pull Requests
Each PR should fulfill a single purpose. Small PRs are easier and faster to review, leave less room for bugs, and provide a clearer history of changes. If your change touches multiple concerns, split it into separate PRs.
2. Provide Context and Guidance
Reviewers should not have to guess what your PR does or why. Write clear titles and descriptions, link related issues, and guide reviewers through the changes — especially when the PR touches multiple files.
3. Review Your Own Work First
Before requesting review, read through your own diff. Build and test locally. Catch typos, leftover debug code, and missing edge cases before someone else does.
4. Keep Your Team Informed
Use labels, linked issues, and project boards to make progress visible. A well-structured PR doubles as a status update — reducing the need for separate check-ins.
5. Respond Constructively to Feedback
Address every review comment. Push fixes as new commits during review so reviewers can track incremental changes. Re-request review only after all feedback is addressed.
Actions
Step-by-step procedures for each phase of raising a pull request:
- Prepare Pull Request — Scope, self-review, and readiness checks before opening
- Write PR Description — Craft a clear title, description, and reviewer guidance
- Submit Pull Request — Open the PR, assign reviewers, and add labels
- Respond to Review — Address feedback, push fixes, and re-request review
- Review Pull Request — Review someone else's PR with constructive feedback
What ships with it
10 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.
- actions/prepare-pull-request.md 3.5 KB
- actions/respond-to-review.md 4.0 KB
- actions/review-pull-request.md 4.1 KB
- actions/submit-pull-request.md 3.5 KB
- actions/write-pr-description.md 3.6 KB
- standards/checklist.md 2.5 KB
- standards/pr-descriptions.md 3.4 KB
- standards/pr-size.md 2.7 KB
- standards/pull-request-template.md 911 B
- standards/self-review-checklist.md 2.5 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.
- 1mo ago First seen · 74 lines · 82 tokens per session scan A e9b75a952472
raise-pull-requests is a skill published in the GitHub repository willvelida/code-minions (23 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 876 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 2026-08-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…