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 agentmods add skills/orlando-japan/claude-code-setting/create-prnpx skills add orlando-japan/claude-code-setting --skill create-prgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/create-pr)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/create-pr"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/create-pr.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00670 |
| Opus 5 | $0.00014 | $0.00335 |
| Sonnet 5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR
A good PR has a clear title, an explained why, and a test plan. A bad PR has "WIP" in the title and 900 files changed.
Before opening
- Rebase on latest main. Stale branches get bounced.
- Squash WIP commits. Your history is your problem; reviewers shouldn't see 40 "fix typo" commits.
- Self-review the diff first. Open it in the GitHub UI and read it like a reviewer. Remove noise, commented-out code, stray
console.log. - Confirm all tests pass locally. Don't outsource detection of obvious failures to CI.
Title
One line, ≤70 chars. Format: <type>: <what and for whom>.
- Good:
fix(auth): redirect logged-out users with return_to param - Bad:
WIP fixes - Bad:
Update auth.ts - Bad:
Refactor everything in the middleware to be cleaner and more maintainable and also fix the bug
Description structure
## Summary
<1-3 bullets. What changed and why. Not "what files changed" — the diff shows that.>
## Context
<Optional. Only if the why isn't obvious. Link to the incident / ticket / design doc that forced this.>
## Test plan
- [ ] <concrete, runnable check #1>
- [ ] <concrete, runnable check #2>
- [ ] <concrete, runnable check #3>
## Screenshots
<If UI changed. Before/after pair if possible.>
## Risks / rollout notes
<Optional. Any migration, flag, feature gate, or order-dependent deploy.>
Test plan items — concrete > abstract
- Good:
[ ] Run pnpm test auth.test.ts — all 8 tests pass - Good:
[ ] As a logged-out user, visit /settings — redirects to /login?return_to=/settings - Bad:
[ ] Tested locally - Bad:
[ ] No regressions
Size
- Target: <400 lines of diff for a reviewable PR.
- If larger: is this really one change, or should it split? Multi-commit stacked PRs often beat one mega-PR.
- Never rename + refactor + add feature in one PR. Each deserves its own.
After opening
- Don't force-push unless you rebase on main or squash at the end. Force-pushing destroys review threads.
- Reply to every comment. "Fixed" is fine. Unanswered comments make reviewers think you ignored them.
- Don't merge your own PR unless policy allows. Ask someone.
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.
- 4d ago First seen · 76 lines · 27 tokens per session scan A 39f75c0f09dc
create-pr is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 670 once invoked, about $0.0001 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
pr-triage
PR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
ask-copilot
Use GitHub Copilot CLI in non-interactive mode to ask questions, review code, or generate snippets without manual interaction.
pr-review
Review a GitHub pull request and post one formal review — advance the existing discussion and give precision-first, high-signal feedback. Judgement on the diff, not a build gate — CI validates that it builds, and a targeted probe is allowed as evidence. Use when asked to review a PR or on a cron PR scan.
security-review
Diff-scoped security review of SDLC concerns GitHub's scanners miss — workflow/CI hardening, auth changes, secret handling, supply-chain churn. Files one dated summary issue with a task-list of findings. Use on a security cron or when asked to scan a repo.
GitHubレビューコメント対応（修正案つき）
PRレビューコメントを重要度ごとに整理し、対応方針・修正案・質問をまとめて返信案を作る.
pr-triage
Context-efficient PR comment triage. Evaluate, decide, act. Fix important issues, resolve the rest silently.