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 semantic-szz-analyzergit 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/semantic-szz-analyzer)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/semantic-szz-analyzer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/semantic-szz-analyzer/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/semantic-szz-analyzer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/semantic-szz-analyzer.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 | $0.00096 | $0.01273 |
| Opus 5.5 | $0.00038 | $0.00509 |
| Sonnet 5.5 | $0.00019 | $0.00255 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
semantic-szz-analyzer 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic SZZ Analyzer
Overview
Semantic SZZ Analyzer extends the traditional SZZ (Sliwerski-Zimmermann-Zeller) algorithm by incorporating semantic analysis to identify bug-introducing commits more accurately. It distinguishes actual semantic changes from refactorings or code movements by analyzing control-flow and data-flow similarity across versions.
Core Capabilities
1. Semantic Change Detection
Analyze commits to distinguish between:
- Semantic changes: Modifications that alter program behavior
- Refactorings: Code restructuring without behavior changes
- Code movements: Relocations of code blocks without semantic impact
Use control-flow graphs (CFG) and data-flow analysis to compute similarity between code versions.
2. Bug-Introducing Commit Identification
Given a bug-fix commit, trace back through git history to identify the commit that introduced the bug:
- Extract changed lines from the bug-fix commit
- Use
git blameto find commits that last modified those lines - Apply semantic analysis to filter out false positives
- Rank candidates by semantic similarity and temporal proximity
3. False Positive Reduction
Traditional SZZ produces many false positives due to:
- Whitespace changes
- Comment modifications
- Import reorganization
- Variable renaming
- Code formatting
Semantic SZZ filters these by analyzing AST (Abstract Syntax Tree) structure and semantic equivalence.
Workflow
Step 1: Analyze Bug-Fix Commit
Start by identifying the bug-fix commit. Look for:
- Commits with keywords: "fix", "bug", "issue", "patch", "resolve"
- Commits linked to issue trackers
- Commits explicitly marked as fixes
Extract the changed lines and affected files.
Step 2: Identify Candidate Commits
Use git blame or git log -L to trace the history of changed lines:
git blame -L <start>,<end> <file> <bug-fix-commit>^
This identifies commits that last modified the buggy lines before the fix.
Step 3: Apply Semantic Analysis
What ships with it
8 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 · 172 lines · 96 tokens per session scan A 9de1f003cc68
semantic-szz-analyzer is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (259 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,273 once invoked, about $0.0004 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 2026-09-03.
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.