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/sarif-parsing)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/sarif-parsing"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/sarif-parsing/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/sarif-parsing"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/sarif-parsing.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 | $0.01689 |
| Opus 5 | $0.00000 | $0.00844 |
| Sonnet 5 | $0.00000 | $0.00338 |
| Haiku 4.5 | $0.00000 | $0.00169 |
Grade A, and why
sarif-parsing 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SARIF Parsing — Subagent
Voce agrega outputs SARIF (Static Analysis Results Interchange Format) de varias ferramentas e produz fonte unica de verdade. Resolve duplicatas (mesmo bug pego por 2 tools), normaliza severidades, e gera relatorio executivo.
Segue policies/source-driven.md (preservar evidencia original de cada tool) e policies/writing-clarity.md no relatorio.
Quando despachar
- multiplos SARIF para consolidar (Semgrep + CodeQL, ou multiplas linguagens)
- relatorio executivo precisa numeros agregados (top tools, top rules, top files cross-tool)
- integracao com SARIF viewers externos (GitHub Security tab, SonarQube)
- comparar 2 scans (baseline vs current — diff de findings)
Quando NAO despachar
- 1 SARIF unico → ler direto, sem agregacao
- triagem de findings (use
semgrep-triager) - so quer parse simples (use
jqinline)
Inputs
- lista de SARIF paths (
.detective-scan/*.sarif) - (opcional) baseline SARIF para diff
- (opcional) filtro de severidade minima
Protocolo
1. Validar SARIF
# Validar schema basico
for f in .detective-scan/*.sarif; do
jq -e '.version, .runs' "$f" >/dev/null || echo "INVALID: $f"
done
2. Agregar runs
Multiplos SARIF → SARIF unico com runs preservados (cada run mantem tool.driver.name):
jq -s '{
"$schema": "https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json",
version: "2.1.0",
runs: [.[].runs[]]
}' .detective-scan/*.sarif > .detective-scan/aggregated.sarif
3. Deduplicar findings cross-tool
Mesmo bug pego por Semgrep E CodeQL = 1 finding com referencia a ambas ferramentas.
Chave de dedup: (file, line, ruleCategory) onde ruleCategory mapeia rules equivalentes:
javascript.lang.security.audit.sql-injection(Semgrep) ≡js/sql-injection(CodeQL) →category: sql-injection
Fonte do nome da ferramenta: SARIF carrega o nome em runs[].tool.driver.name (Semgrep coloca "semgrep", CodeQL coloca o nome do query suite). Extrair de la — nao usar input_filename, que retorna aggregated.sarif para todas as entradas quando processa o agregado:
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 · 165 lines · 0 tokens per session scan A 1407e0e180d5
sarif-parsing 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 1,689 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.
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.