semgrep-scanner

semgrep-scanner is an agent for Claude Code from felvieira/claude-skills-fv. It costs 78 tokens per session (1,350 once invoked), scanned A, original, Apache-2.0.

A Semgrep scanning subagent for codebases that use two or more programming languages. Semgrep is a tool that searches source code for security problems and bugs using rules, and SARIF is a standard format for storing scan findings.

In plain words
What is it for?
It is for running parallel Semgrep scans across languages such as TypeScript, Python, Go, and Rust, then aggregating the findings for security or bug triage.
Why use it?
It avoids running separate language scans one at a time and combines the results into one file for review.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit It is for running parallel Semgrep scans across languages such as TypeScript, Python, Go, and Rust, then aggregating the findings for security or bug triage.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felvieira/claude-skills-fv/semgrep-scanner
Install

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.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

Wrote 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.

agentmods badge for semgrep-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/semgrep-scanner/github.svg)](https://agentmods.dev/agents/felvieira/claude-skills-fv/semgrep-scanner)
Your own site
<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.

agentmods 80×15 button for semgrep-scanner

Your own site · 80×15
<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>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 2f4fd95111f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

agents/semgrep-scanner.md · 156 lines

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

Read the full file on GitHub · 156 lines

Changes

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.

  1. 12d ago First seen · 156 lines · 78 tokens per session scan A 2f4fd95111f4

Subscribe to this mod's changes

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.