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 oxbshw/LLM-Agents-Ecosystem-Handbook --skill pr-summarizergit clone --depth 1 https://github.com/oxbshw/LLM-Agents-Ecosystem-HandbookWrote 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/oxbshw/llm-agents-ecosystem-handbook/pr-summarizer)<a href="https://agentmods.dev/skills/oxbshw/llm-agents-ecosystem-handbook/pr-summarizer"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/pr-summarizer/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/oxbshw/llm-agents-ecosystem-handbook/pr-summarizer"><img src="https://agentmods.dev/badge/skills/oxbshw/llm-agents-ecosystem-handbook/pr-summarizer.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 | $0.00034 | $0.00457 |
| Opus 5 | $0.00017 | $0.00229 |
| Sonnet 5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
pr-summarizer 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 12d 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.
What it actually says
PR Summarizer
When to use
- Just before opening a PR
- After force-pushing a substantive update to an existing PR (refresh description)
When NOT to use
- Drafts the user is still iterating on (the summary will go stale immediately)
- Massive diffs (> 1000 lines) — ask the user to scope first
Inputs
| Name | Type | Required | Notes |
|---|---|---|---|
base |
string | no | default origin/main |
branch |
string | no | default current HEAD |
Outputs
A markdown PR body with sections: Summary, Why, How tested, Risks, Linked.
Workflow
git diff <base>...HEAD --statandgit log <base>..HEAD --onelineto see scopegit diff <base>...HEADfor content- Group changes by area (one bullet per logical concern, not per file)
- Pull "why" from commit messages + linked tickets if mentioned
- Identify test artifacts touched; surface as How tested (or flag if none)
- Risks: any High-risk paths touched? auth, billing, migrations? mention.
- Linked: parse
Fixes #/Refs #from commits
References
Success criteria
- Description ≤ 25 lines
- Every "why" claim is supported by a commit message or visible in the diff
- Risks section honest about unknowns ("untested in production data shape")
Failure modes
- No commit messages worth quoting → "Why" sourced from diff only; flag this
- Diff touches secrets /
.env*→ STOP and surface; PR shouldn't include them
What ships with it
1 file 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.
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.
- 12d ago First seen · 49 lines · 34 tokens per session scan A 495397162b01
pr-summarizer is a skill published in the GitHub repository oxbshw/LLM-Agents-Ecosystem-Handbook (546 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 457 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ce-worktree
Set up isolated git worktrees — create a new branch for fresh work, or attach a worktree to an existing branch, PR, or commit. Use when starting isolated work or isolating an existing ref.
ce-commit
Create a git commit with a clear, value-communicating message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate message.
ce-babysit-pr
Babysits an open GitHub PR until merge-ready. Use when asked to watch a PR over time — not for one-shot comment resolution or one CI failure. GitHub (incl. Enterprise) only.
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
ce-resolve-pr-feedback
Resolve PR review feedback. Use when addressing feedback already left on a PR. Not for reviewing the code before feedback exists; that is ce-code-review.
git-workflow
Use this skill when working with git — making commits, creating branches, resolving merge conflicts, opening pull requests, or reviewing diffs. Apply whenever the user asks about version control operations.