Semgrep Triager — Research agent for Claude Code
Classifies semgrep scan findings as true or false positives by reading source context.
How to install Semgrep Triager
Installs to ~/.claude/agents/samg0ld-claude-code-starter-semgrep-triager.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/SamG0ld/claude-code-starter/HEAD/agents/semgrep-triager.md -o ~/.claude/agents/samg0ld-claude-code-starter-semgrep-triager.md Restart Claude Code, or start a new session, for it to be picked up.
What Semgrep Triager does
name: semgrep-triager description: "Classifies semgrep scan findings as true or false positives by reading source context. Use when triaging static analysis results to separate real vulnerabilities from noise." tools: Read, Grep, Glob, Write model: sonnet
Semgrep Triage Agent
You are a security finding triager responsible for classifying Semgrep scan results as true or false positives by reading source code context.
Task
For each finding in the provided JSON result files:
- Re
Alternatives in Research
- Fable Worker Sonnet — Fable stage worker for tasks needing real reasoning — research synthesis, nontrivial code, analysis, document 837 ★
- Paper Crawler — Collects and classifies research papers from DBLP and OpenAlex APIs for literature surveys 169 ★
- Claude Code MCP Behavior Analysis — Results from 15 tests against a minimal Cord MCP server 133 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Hydra-sentinel — Deep Integration Analysis
You are the deep analysis layer. You run ONLY when hydra-sentinel-scan has flagged potential integration issue
Contradiction Reasoner
Contradiction Reasoner — Deep Probe Phase 5 hypothesis generator applying TRIZ Contradiction Analysis and Game
Thrunt Signal Triager
Researches domain ecosystem before huntmap creation. Produces files in .planning/research/ consumed during hun
Numba-accelerated Multi-timeframe Analysis
@nb.njit(fastmath=True, cache=True, parallel=True) def compute_multiscale_momentum(prices, volumes, scales=10
Analista
Intelligence advisor of the workbench. Invoke when the operator asks for a briefing, status, summary or analys
Competitor Analyzer
Deep autonomous competitor research — multi-pass crawl across 5+ competitors with full backlink delta, 1000+-t
Related Skills
Makoto
When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deed
Audit Strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Agg
Cpv Batch Validate And Fix
Same-turn validate-and-fix across a marketplace / list / single plugin. One cpv-plugin-fixer-agent per plugin