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 oguzsh/claudey --skill pr-describegit clone --depth 1 https://github.com/oguzsh/claudeyWrote 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/oguzsh/claudey/pr-describe)<a href="https://agentmods.dev/skills/oguzsh/claudey/pr-describe"><img src="https://agentmods.dev/badge/skills/oguzsh/claudey/pr-describe/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/oguzsh/claudey/pr-describe"><img src="https://agentmods.dev/badge/skills/oguzsh/claudey/pr-describe.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 | $0.00050 | $0.00620 |
| Opus 5 | $0.00025 | $0.00310 |
| Sonnet 5 | $0.00010 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
pr-describe 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 10d 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.
PR Description Generator
Generate a comprehensive, structured pull request description by analyzing the current branch's git history and diff against the base branch.
Workflow
Step 1: Detect base branch and gather changes
- Determine the base branch. Default to
mainunless the user specifies otherwise. - Run these git commands to gather all changes on the current branch:
# Get current branch name
git rev-parse --abbrev-ref HEAD
# Get commit log since diverging from base
git log main...HEAD --oneline --no-merges
# Get full diff against base
git diff main...HEAD
- If the diff is very large, also run
git diff main...HEAD --statfor a file-level summary to help with the high-level overview.
Step 2: Analyze changes and generate description
Analyze all commits and the full diff to populate each section of the template below. Be thorough - read the actual code changes, not just commit messages.
Guidelines for each section:
- What? - Concise summary of what the PR does. Use bullet points for multiple changes. Focus on observable behavior changes and new capabilities.
- Why? - Explain the motivation. What problem does this solve? What ticket or initiative does it relate to? Infer from branch name, commit messages, and code context.
- Architecture - Include a mermaid diagram ONLY when changes involve architectural patterns: new modules, service layers, API routes, data flow changes, new abstractions, or significant structural reorganization. Skip this section entirely for simple bug fixes, config changes, or minor updates.
- How it works? - Explain the implementation approach. Walk through the key changes and how they connect. Mention important design decisions.
- How can I test the branch? - Provide concrete, actionable test steps. Include specific commands to run tests, endpoints to hit, or scenarios to verify. Reference specific test files if tests were added/modified.
Step 3: Output the description
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.
- 10d ago First seen · 76 lines · 50 tokens per session scan A 9e1c38715d49
pr-describe is a skill published in the GitHub repository oguzsh/claudey (5 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 620 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…