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 agentmods add skills/ckorhonen/swe-skills/recent-commit-bug-huntnpx skills add ckorhonen/swe-skills --skill recent-commit-bug-huntgit 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/recent-commit-bug-hunt)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/recent-commit-bug-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/recent-commit-bug-hunt.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.01524 |
| Opus 5 | $0.00050 | $0.00762 |
| Sonnet 5 | $0.00020 | $0.00305 |
| Haiku 4.5 | $0.00010 | $0.00152 |
Grade A, and why
swe:recent-commit-bug-hunt 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 6d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Recent Commit Bug Hunt
What This Skill Does
Use this skill to inspect recent code changes conservatively and separate:
- Real regression signals
- Plausible but weaker suspicions
- Noise that should not become a fix proposal
The outcome should be a ranked list of evidence-backed findings plus small, behavior-focused remediation sessions for the findings that clear the bar.
When To Use
Use this skill when the user wants to:
- Review recent commits for likely regressions
- Check whether their latest changes introduced bugs
- Mine recent PRs or SHAs for concrete bug signals
- Propose narrowly scoped follow-up fix sessions
Do Not Use
Do not use this skill for:
- A generic code smell review
- A security or dependency audit
- A large-scale refactor plan
- Speculative bug hunting with no commit scope
Inputs To Confirm
Confirm or infer:
- Repository set
- Author filter, if any
- Time window
- Whether linked PR or CI context is available
- Whether local validation can be run
If scope is missing, ask for the repo set, author, and timeframe before proceeding.
Evidence Sources
Concrete evidence includes:
- Commit SHAs
- Pull requests
- File paths
- Diffs
- Failing tests
- CI failures or warnings
- Local validation signals directly tied to the changed area
If the evidence is weak, report the suspicious finding and skip the fix proposal.
Hard Constraints
- Use only concrete repo evidence
- Do not invent bugs
- Do not overstate confidence
- Do not propose speculative fixes when the evidence is weak
- Prioritize the smallest safe fix possible
- Avoid refactors, cleanup work, or unrelated improvements
- Keep each remediation proposal tightly scoped to the implicated files and behavior
Instructions
Step 1: Define The Review Scope
Respect the user-provided repository set, author filter, and time window exactly.
If the user names a repo group or org surface, stay within that scope.
Step 2: Collect Recent Changes And Context
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.
- 6d ago First seen · 250 lines · 100 tokens per session scan A d8cc3eb9462d
swe:recent-commit-bug-hunt is a skill published in the GitHub repository ckorhonen/swe-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,524 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
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
gsd-audit-fix
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.
git-worktree-precommit-hook-flutter-failure
Fix git pre-commit hook failures in Flutter projects when using git worktrees. Use when: (1) Pre-commit hook with flutter analyze fails during git commit but passes when run manually, (2) Hook output shows "Resolving dependencies..." then immediately fails with no actual analysis errors, (3) Working in a git worktree…
git-mastery
Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.
git-bisect-assistant
Automatically performs git bisect to identify the first bad commit that introduced a bug or failure. Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality. Handles flaky tests with retry logic and provides comprehensive reports with bisect logs and…
semantic-szz-analyzer
Identify bug-introducing commits using semantic analysis that extends traditional SZZ algorithm. Distinguishes semantic changes from refactorings or code movements using control-flow and data-flow similarity analysis. Use when analyzing bug-fix commits to trace back to bug-introducing changes, investigating software…