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 ArabelaTso/Skills-4-SE --skill szz-bug-identifiergit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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/arabelatso/skills-4-se/szz-bug-identifier)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/szz-bug-identifier"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/szz-bug-identifier/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/arabelatso/skills-4-se/szz-bug-identifier"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/szz-bug-identifier.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 | $0.00121 | $0.01365 |
| Opus 5.5 | $0.00048 | $0.00546 |
| Sonnet 5.5 | $0.00024 | $0.00273 |
| Haiku 4.5 | $0.00012 | $0.00136 |
Grade A, and why
szz-bug-introducing-commit-identifier scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SZZ Bug-Introducing Commit Identifier
Overview
This skill performs SZZ (Śliwerski-Zimmermann-Zeller) algorithm analysis to identify bug-introducing commits in git repositories. Given a bug-fixing commit, it traces modified lines back through version history using git blame to find candidate commits that originally introduced the buggy code.
Workflow
1. Identify the Bug-Fixing Commit
Start by identifying the commit that fixes the bug. This can be obtained from:
- Commit hash provided by the user
- Issue tracker references (e.g., "fixes #123")
- Commit message analysis (e.g., "fix:", "bug:")
- Manual identification by the user
2. Run the SZZ Analysis
Use the provided script to perform the analysis:
python scripts/szz_analyzer.py <fix-commit-hash>
Options:
--repo <path>: Specify repository path (default: current directory)--json: Output results in JSON format for programmatic processing--top <n>: Number of top candidates to show (default: 10)
Example:
python scripts/szz_analyzer.py abc123def --repo /path/to/repo --top 5
3. Interpret Results
The script outputs a ranked list of candidate bug-introducing commits with:
- Commit hash: The candidate commit identifier
- Author: Who made the commit
- Date: When the commit was made
- Message: The commit message
- Confidence score: Likelihood this commit introduced the bug (0.0-1.0)
- Reasons: Explanation for why this commit is a candidate
4. Manual Verification
Always manually review the top candidates:
- Examine the actual code changes in the candidate commit
- Check if the changes are functionally related to the bug
- Consider the context and purpose of the changes
- Verify against issue tracker history if available
Understanding Confidence Scores
High Confidence (0.8-1.0):
- Multiple lines from the commit were fixed
- Commit message doesn't suggest refactoring
- Functional code changes (not just formatting)
What ships with it
2 files 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.
- 1mo ago First seen · 183 lines · 121 tokens per session scan A 111025974e9e
szz-bug-introducing-commit-identifier is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (259 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,365 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
lineage
Use when asked why code exists or why it works the way it does - "why is this here", "why did we pick Y", "who added this and for what", "is it safe to remove", a regression's origin, a magic threshold, or a workaround with no comment - and before deleting or reshaping code whose reason you cannot see.
fix-issue
Fix a GitHub issue end-to-end -- read the issue, implement the fix, write tests, and create a commit. Use when you want to fix a specific GitHub issue, resolve a bug report, or implement a feature request.
skill-pr-review
Comprehensive code review for pull requests using parallel multi-agent analysis. Audits CLAUDE.md compliance, checks for bugs, analyzes git history, reviews comments, and filters by confidence score. Use when reviewing a GitHub PR, mentions "code review", "review this PR", or "/code-review".
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
skill-incident-management
Incident response, postmortem facilitation, root cause analysis (RCA), blameless culture, incident timeline documentation, and incident classification. Use when responding to production incidents, writing incident reports, facilitating postmortems, or improving incident response processes.