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 LerianStudio/ring --skill generating-pr-descriptionsgit clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/generating-pr-descriptions)<a href="https://agentmods.dev/skills/lerianstudio/ring/generating-pr-descriptions"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/generating-pr-descriptions/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/lerianstudio/ring/generating-pr-descriptions"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/generating-pr-descriptions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01595 |
| Opus 5.5 | $0.00024 | $0.00638 |
| Sonnet 5.5 | $0.00012 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
ring:generating-pr-descriptions 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating PR Descriptions
When to use
- Preparing a pull request for review and need a comprehensive description
- Generating a PR title automatically from commit message analysis
- Classifying the type of change (bug fix, feature, breaking change)
- Saving a reusable PR description to
docs/pr-descriptions/<branch-name-with-hyphens>.md
Skip when
- The PR is a single trivial commit with an obvious description
- A PR description already exists and does not need regeneration
- The branch has no commits beyond the base branch
Process
1. Git Branch Analysis - CRITICAL: Branch-Only Scope
- MANDATORY: Identify actual branch point to avoid analyzing entire development history
- Detect the base branch (develop, main, master) that the current branch was created from
- CORRECT APPROACH: Use
git merge-base HEAD <base-branch>to find the true divergence point - CORRECT APPROACH: Use
git log --oneline $(git merge-base HEAD <base-branch>)..HEADfor branch-specific commits - CORRECT APPROACH: Use
git diff $(git merge-base HEAD <base-branch>)..HEADfor branch-specific changes - NEVER rely on manual
HEAD~ncounting — it breaks on merges, rebases, and long-lived branches - Run
git status --porcelainto identify uncommitted files (excluded from PR) - Enforce that PR analyzes ONLY commits made on the current feature branch, not development history
- Determine if this is a bug fix, feature, or breaking change based on actual branch commits
2. Change Classification
- Analyze file patterns and change types
- Identify the type of change (bug fix, new feature, breaking change, etc.)
- Detect if documentation updates are needed
- Determine testing requirements
3. PR Description Generation
- Create comprehensive description following the template format
- Include summary of changes and motivation based on ONLY branch-specific commits
- Pre-fill appropriate checkboxes based on change analysis
- Suggest testing strategies
- Derive the output filename from the full branch name with slashes replaced by hyphens (e.g.,
feature/FE-157->feature-FE-157.md) - Save to
docs/pr-descriptions/<derived-filename>(create directory if needed)
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 · 169 lines · 61 tokens per session scan A 4ab5861d8e71
ring:generating-pr-descriptions is a skill published in the GitHub repository LerianStudio/ring (218 stars, last pushed 7d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,595 once invoked, about $0.0002 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
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
commit
Create a user-requested Conventional Commit from the staged changes.
mr
Create a merge request or pull request from the current branch: verify quality gates, enforce conventional commits, validate the title, preview, and wait for explicit approval before creating. Use when the user says 'create MR', 'create PR', 'open a merge request', or 'raise a PR'.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.