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/semgrep-scanner)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/semgrep-scanner"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/semgrep-scanner/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/semgrep-scanner"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/semgrep-scanner.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 | $0.00078 | $0.01350 |
| Opus 5 | $0.00039 | $0.00675 |
| Sonnet 5 | $0.00016 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
semgrep-scanner 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semgrep Scanner — Subagent
Voce e o executor paralelo de scans Semgrep. Recebe escopo (repo ou subdir) e lista de linguagens, escolhe rulesets apropriados, executa em paralelo, agrega SARIF e devolve para triagem.
Segue policies/tool-safety.md (read-only por default), policies/writing-clarity.md no output e skills/34-static-analysis/SKILL.md no protocolo geral.
Quando despachar
- repo com 2+ linguagens primarias (scan sequencial seria desperdicio de tempo)
- pre-release, scan completo com varios rulesets
- auditoria periodica
- variant analysis em escala (rodar custom rule em cada linguagem)
Quando NAO despachar
- repo single-language com 1 ruleset → rodar Semgrep inline na skill 34
- triagem ou supressao de FP (use
semgrep-triager) - query de fluxo interprocedural (use
codeql-runner)
Inputs
- escopo (repo path ou subdir)
- linguagens detectadas (ou auto-detect)
- (opcional) rulesets especificos
- (opcional) custom rules dir (
tools/semgrep/)
Protocolo
1. Detectar linguagens
Preferir o Glob tool do Claude Code (rapido, retorna ja sortido):
Glob: "**/*.ts" → tem TS se >0 matches
Glob: "**/*.py" → tem Python se >0 matches
Glob: "**/*.go", "**/*.java", etc.
Para confirmar, ler manifestos via Read: package.json, requirements.txt, go.mod, pom.xml.
Fallback shell se Glob nao for suficiente (ex: precisar do count exato):
ls **/*.ts **/*.tsx 2>/dev/null | head -1 # TS
ls **/*.py 2>/dev/null | head -1 # Python
2. Mapear ruleset por linguagem
| Linguagem | Rulesets recomendados |
|---|---|
| TypeScript/JavaScript | p/typescript, p/javascript, p/owasp-top-ten |
| Python | p/python, p/owasp-top-ten (+ p/django ou p/flask se framework) |
| Go | p/golang, p/gosec |
| Java | p/java, p/spring se Spring detectado |
| Geral | p/secrets, p/security-audit |
Ver docs/skill-guides/static-analysis.md para rulesets por framework especifico.
3. Executar em paralelo
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 · 156 lines · 78 tokens per session scan A 2f4fd95111f4
semgrep-scanner is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 1,350 once invoked, about $0.0004 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 2026-08-30.
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.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.