Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/rjmurillo/ai-agents/validate-pr-description)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/validate-pr-description"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/validate-pr-description/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/rjmurillo/ai-agents/validate-pr-description"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/validate-pr-description.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 | $0.00084 | $0.01796 |
| Opus 5.5 | $0.00034 | $0.00718 |
| Sonnet 5.5 | $0.00017 | $0.00359 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
validate-pr-description 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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate PR Description
Check a PR title and body against the three things this repository's gates read: the conventional-commit title, the issue-linking keyword, and the template sections the spec-coverage job parses. Catch them before submission, where the fix costs one edit instead of one CI round.
Migrated from .claude/commands/validate-pr-description.md under ADR-064, which
makes skills the single user-invocable surface. user-invocable: true is what
fires it as /validate-pr-description in both Claude Code and Copilot CLI.
Triggers
validate my PR description, check my PR title, is this PR body compliant,
validate PR metadata
Inputs
| Input | Source | Required |
|---|---|---|
| PR title | $0, or stated in conversation |
Yes |
| PR body | $1 as a path to a file, or pasted text |
Yes |
| Target repository | current checkout | Yes |
Process
Phase 1: Resolve the inputs
Read the title and body from the arguments when given. When they are not, ask for both rather than inferring them from the branch or the last commit: a PR body is usually longer than any commit message, and validating the wrong text reports a pass that does not describe the PR.
When the body arrives as a path, read the file. When it arrives as pasted text, work from the text directly.
Phase 2: Run the three checks
| # | Check | Rule | Failure meaning |
|---|---|---|---|
| 1 | Conventional commit title | <type>(<scope>)?: <description>, type one of feat, fix, docs, style, refactor, perf, test, chore, ci, build, revert |
Release tooling cannot classify the change |
| 2 | Issue-linking keyword | body holds at least one of Closes #N, Fixes #N, Resolves #N, or a past-tense variant |
The issue stays open after merge, and the PR fails the repository's issue-linkage rule |
| 3 | Template compliance | Summary non-empty, Changes has at least one item, Type of Change has at least one marked checkbox | The spec-coverage job reports FAIL on an unpopulated section |
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.
- 3d ago Changed · +28 lines 532122501a65
- 22d ago Changed · +6 lines 35b80fc1ec64
- 1mo ago First seen · 113 lines · 84 tokens per session scan A 07e5b157dcb2
validate-pr-description is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,796 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 2026-09-08.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
merge-queue
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
ase-repo-review
Perform a holistic, human-reviewer-style critique of the currently staged Git changes (or, with --unstaged, of the unstaged and untracked changes, with --branch, of a branch against its base, or, with --commit, of a single commit) and emit an approve/reject verdict with prioritized, severity-tagged, line-cited…
shared-tooling-git-hooks
Husky v9 setup, lint-staged v16 patterns, commitlint with conventional commits, CI/production handling, monorepo setup, migration from v8.
apex-host-git-commit
Stage scoped changes, commit, push, and offer a PR in Agent Host. Use /apex-host-git-commit only after selecting the built-in agent owner and MAI-Code-1.1-Flash.