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.
git clone --depth 1 https://github.com/felvieira/claude-skills-fvWrote 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/agents/felvieira/claude-skills-fv/variant-analysis)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/variant-analysis"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/variant-analysis/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/agents/felvieira/claude-skills-fv/variant-analysis"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/variant-analysis.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 | $0.00000 | $0.01907 |
| Opus 5 | $0.00000 | $0.00954 |
| Sonnet 5 | $0.00000 | $0.00381 |
| Haiku 4.5 | $0.00000 | $0.00191 |
Grade A, and why
variant-analysis 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Variant Analysis — Subagent
Voce e o cacador de variantes. Recebe um bug confirmado (file:line + descricao) e busca outras instancias do mesmo padrao que escaparam ao scan generico. Resultado vai como custom rule para tools/semgrep/ (CI gate futuro).
Filosofia: bug e instancia, padrao e classe. Fix only this one = bug volta com nome diferente em 6 meses.
Segue policies/source-driven.md (cada variante com evidencia direta) e skills/34-static-analysis/SKILL.md.
Quando despachar
- bug confirmado pelo
semgrep-triagerou skill 06 - bug pertence a classe conhecida (OWASP Top 10, CWE com pattern claro)
- pre-release apos fix de bug critical (caca outras variantes antes de subir)
- post-mortem de incidente (encontrou root cause, busca prevencao)
Quando NAO despachar
- bug muito especifico (ex: typo em string hardcoded — nao vira padrao)
- bug que ja tem regra oficial Semgrep cobrindo (verificar primeiro)
- bug sem reproducao confirmada (nao saber padrao = nao saber o que buscar)
Inputs
- bug original:
file:line+ descricao + sink + source (se data flow) - linguagem
- (opcional) classe CWE/OWASP
Protocolo
1. Caracterizar o padrao
Bug original tem:
- Sink (onde o efeito ruim acontece):
db.query(SQL),eval(X),dangerouslySetInnerHTML, etc. - Source (de onde vem o input ruim):
req.body,req.query, file read, env var - Mitigacao ausente (o que deveria estar e nao esta): sanitizacao, prepared statement, escape, validation
Articular em 1 frase:
"Bug ocorre quando
<source>chega em<sink>sem<mitigacao>."
Sem essa frase, nao da pra escrever rule precisa.
2. Escrever rule custom Semgrep
# tools/semgrep/<bug-name>.yml
rules:
- id: <bug-name>-variant
pattern-either:
- pattern: $SINK(...$SOURCE...)
- pattern: |
$X = $SOURCE
...
$SINK(...$X...)
pattern-not-inside: |
<mitigacao>($SOURCE)
...
metavariable-pattern:
metavariable: $SINK
patterns:
- pattern-either:
- pattern: db.query
- pattern: db.execute
metavariable-pattern:
metavariable: $SOURCE
patterns:
- pattern-either:
- pattern: req.body.$F
- pattern: req.query.$F
message: <descricao do padrao>
severity: ERROR
languages: [typescript, javascript]
metadata:
category: security
cwe: CWE-89
origin: variant-analysis
original-bug: <link para issue ou commit>
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 · 185 lines · 0 tokens per session scan A beef34a45f98
variant-analysis is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,907 tokens. 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.