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 ckorhonen/swe-skills --skill pr-risk-reviewgit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/pr-risk-review)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/pr-risk-review"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/pr-risk-review/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/ckorhonen/swe-skills/pr-risk-review"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/pr-risk-review.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 | $0.00101 | $0.01257 |
| Opus 5 | $0.00051 | $0.00629 |
| Sonnet 5 | $0.00020 | $0.00251 |
| Haiku 4.5 | $0.00010 | $0.00126 |
Grade A, and why
swe:pr-risk-review 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE PR Risk Review
What This Skill Does
Use this skill to review an open or draft pull request before merge and decide where the engineering risk is concentrated.
The expected outcome is a concise risk report that tells the user:
- what the PR changes
- what makes it risky or low-risk
- what validation is missing or weak
- what rollout, rollback, or migration gaps still need attention
- what the smallest safe next action is
This skill is deliberately narrower than post-merge monitoring and bug hunting. It is about merge readiness, not production impact and not retrospective defect mining.
When To Use
Use this skill when the user wants to:
- review a PR before merge
- decide whether a change is safe to merge
- identify missing tests, checks, or rollout planning on an open PR
- assess whether migrations, flags, or interface changes need extra caution
- get agent-safe follow-up actions without doing the merge
Do Not Use
Do not use this skill for:
- post-merge production monitoring
- scanning recent commits for regressions after the fact
- a broad code style or architecture review with no PR scope
- general project planning or roadmap feedback
- security-specific review when the user explicitly asked for a security audit
Inputs To Confirm
Confirm or infer:
- the PR number, branch, or diff scope
- the repository or service in scope
- whether CI or local validation data is available
- whether the user wants report-only output or a concrete follow-up plan
- any no-touch areas, rollout constraints, or deadlines
If the request is vague, ask for the PR link or number and the intended review focus before proceeding.
Tooling Stance
This skill is tool agnostic.
Use the strongest available evidence from:
- PR metadata and diffs
- CI status or failing checks
- local test or typecheck commands
- migration or rollout notes
- feature-flag or config changes
- release or rollback documentation
Prefer the repository's own validation commands and only broaden if the local signals are insufficient.
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 · 190 lines · 101 tokens per session scan A 7dcbfb4702ca
swe:pr-risk-review is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,257 once invoked, about $0.0005 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
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
create-pull-request
Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
gate-and-merge
Use when landing a queue of open PRs: gate each PR, sweep its review feedback to root cause, then merge, repair, hold, or close it. Human-only.