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/notque/vexjoy-agent/pr-workflownpx skills add notque/vexjoy-agent --skill pr-workflowgit clone --depth 1 https://github.com/notque/vexjoy-agentWrote 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/notque/vexjoy-agent/pr-workflow)<a href="https://agentmods.dev/skills/notque/vexjoy-agent/pr-workflow"><img src="https://agentmods.dev/badge/skills/notque/vexjoy-agent/pr-workflow.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 | $0.00125 | $0.03633 |
| Opus 5 | $0.00063 | $0.01817 |
| Sonnet 5 | $0.00025 | $0.00727 |
| Haiku 4.5 | $0.00013 | $0.00363 |
Grade A, and why
pr-workflow 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Workflow Skill
Umbrella skill for the entire pull request lifecycle. Routes to the correct reference based on the PR task requested.
Routing
Detect the user's intent and load the appropriate reference file:
| Intent | Trigger phrases | Reference |
|---|---|---|
| Sync (default) | "push", "create PR", "sync", "ship this" | ${CLAUDE_SKILL_DIR}/references/sync.md |
| Pipeline | "submit PR", "full PR", "end-to-end PR", "open PR" | ${CLAUDE_SKILL_DIR}/references/pipeline.md |
| Fix | "fix PR comments", "address review", "pr-fix", "resolve feedback" | ${CLAUDE_SKILL_DIR}/references/fix.md |
| Status | "pr status", "branch status", "is my PR ready", "check CI" | ${CLAUDE_SKILL_DIR}/references/status.md |
| Cleanup | "clean up branches", "delete merged branch", "prune" | ${CLAUDE_SKILL_DIR}/references/cleanup.md |
| Feedback | "process PR feedback", "address reviews", "what did reviewers say" | ${CLAUDE_SKILL_DIR}/references/feedback.md |
| Miner | "mine PRs", "extract review comments", "tribal knowledge", "reviewer patterns" | ${CLAUDE_SKILL_DIR}/references/miner.md |
| Branch name | "generate branch name", "validate branch name", "name branch", "branch convention", "git branch name" | ${CLAUDE_SKILL_DIR}/references/branch-name.md |
| CI check | "check CI", "CI status", "actions status", "did CI pass", "build status", "CI passed" | ${CLAUDE_SKILL_DIR}/references/ci-check.md |
| Commit | "commit changes", "stage and commit", "commit my changes", "commit my files", "commit these" | ${CLAUDE_SKILL_DIR}/references/commit.md |
| Codex review | "codex review", "second opinion", "code review codex", "gpt review", "cross-model review" | ${CLAUDE_SKILL_DIR}/references/codex-review.md |
| Land | "land PR", "land the PR", "merge contributor PR", "rebase and merge PR" | ${CLAUDE_SKILL_DIR}/references/land-pr.md |
| Body safety | any gh call writing or reading a PR/issue body |
${CLAUDE_SKILL_DIR}/references/gh-body-safety.md |
| Changelog | "update changelog", "release notes", "curate changelog" | ${CLAUDE_SKILL_DIR}/references/changelog-curation.md |
| Decision brief | "decision brief", "authorization tier", "ask the owner", "is it decision-ready" | ${CLAUDE_SKILL_DIR}/references/owner-decision-briefs.md |
| Risk classify | automatic pre-review step; also "classify PR risk", "pr risk", "risk check" | ${CLAUDE_SKILL_DIR}/references/pr-risk-policy.md |
What ships with it
36 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.
- references/branch-name.md 6.0 KB
- references/changelog-curation.md 1.9 KB
- references/ci-check.md 6.5 KB
- references/cleanup.md 6.8 KB
- references/codex-review-cli-patterns.md 7.3 KB
- references/codex-review-invocation.md 9.0 KB
- references/codex-review-methodology.md 7.5 KB
- references/codex-review-preferred-patterns.md 11 KB
- references/codex-review.md 3.0 KB
- references/commit-banned-patterns.md 11 KB
- references/commit-conventional.md 12 KB
- references/commit-examples.md 7.5 KB
- references/commit-staging-rules.md 12 KB
- references/commit-workflow-examples.md 4.4 KB
- references/commit.md 5.5 KB
- references/examples.md 5.8 KB
- references/feedback.md 9.4 KB
- references/fix.md 7.4 KB
- references/gh-body-safety.md 1.9 KB
- references/imperative-keywords.txt 615 B
- references/index-conflict-resolution.md 1.5 KB
- references/land-pr.md 6.2 KB
- references/miner.md 20 KB
- references/mining-commands.md 4.7 KB
- references/owner-decision-briefs.md 2.9 KB
- references/pattern-categories.md 6.3 KB
- references/pipeline.md 34 KB
- references/pr-risk-policy.md 3.4 KB
- references/reviewer-usernames.md 1.9 KB
- references/status.md 7.6 KB
- references/sync.md 15 KB
- scripts/coordinator-validate.py 6.9 KB runs code
- scripts/miner.py 12 KB runs code
- scripts/validate_message.py 17 KB runs code
- scripts/validate_state.py 17 KB runs code
- scripts/validate.py 2.7 KB runs code
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 First seen · 233 lines · 125 tokens per session scan A 0a85dab0af5e
pr-workflow is a skill published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 3,633 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
commit-with-reflection
Git提交与调试反思报告生成技能。用于分析开发过程中的错误、调试步骤和解决方案,生成结构化的中文反思报告,并创建包含报告引用的Git提交。显式请求词:反思提交、智能提交、生成调试报告、commit with reflection。.
ac-commit-manager
Manage git commits for autonomous coding. Use when committing feature implementations, creating descriptive commits, managing git workflow, or handling version control.
commit
Creates Conventional Commits with pre-commit validation. Triggers: commit, conventional commit, git commit, message.
night-watch
Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.
om-check-and-commit
Verify that the current branch is ready to publish by running every configured validation command in order, fix straightforward failures (including locale-file drift when the repo checks it), and once everything passes commit and push the current branch. Use when the user asks to check the branch, make CI-style…
git-commit
Commit to Git safely: runs tests, security-reviews the diff, strips secrets and dead code, and enforces clean messages. Use before any commit or push.