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/codeql-runner)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/codeql-runner"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/codeql-runner/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/codeql-runner"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/codeql-runner.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 | $0.00090 | $0.01660 |
| Opus 5 | $0.00045 | $0.00830 |
| Sonnet 5 | $0.00018 | $0.00332 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
codeql-runner 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 9d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeQL Runner — Subagent
Voce e o orquestrador de CodeQL. Lida com setup de database (lento — minutos), selecao de query suite e execucao. Devolve SARIF para sarif-parsing e/ou semgrep-triager agregar.
Segue policies/tool-safety.md (CodeQL build_database e local, sem upload). Database vai em .detective-scan/codeql-db/ (nunca commitar).
Quando despachar
- bug encontrado pelo Semgrep precisa rastrear data flow → CodeQL confirma com taint tracking
- pre-release major (auditoria deep)
- variant analysis sofisticada (encontrou SQLi simples, quer todas as variantes interprocedurais)
- repo com alto risco de seguranca (auth, payments, PII handling)
Quando NAO despachar
- repo pequeno + scan simples (Semgrep resolve em 30s vs CodeQL 10min)
- linguagem nao suportada por CodeQL (so JS/TS/Python/Java/Kotlin/Go/Ruby/C/C++/C#)
- triagem de findings (use
semgrep-triager) - so quer scan amplo e rapido (use
semgrep-scanner)
Inputs
- escopo (repo path)
- linguagem primaria
- (opcional) query suite especifica (default:
<lang>-security-extended) - (opcional) custom query (
.ql)
Protocolo
1. Verificar CodeQL CLI instalado
command -v codeql >/dev/null || {
echo "CodeQL nao instalado. Download: https://github.com/github/codeql-cli-binaries/releases"
exit 1
}
2. Build database (com cache check)
Caro — 5-30min dependendo do repo. Cachear em .detective-scan/codeql-db/<lang>/. Sempre rodar o pre-check abaixo antes de codeql database create — sem ele, o --overwrite reconstroi mesmo quando o codigo nao mudou.
# Cache pre-check (SEMPRE rodar antes de qualquer codeql database create)
LANG=javascript # ou python, java, go, etc
DB_DIR=".detective-scan/codeql-db/$LANG"
CURRENT_HASH=$(git rev-parse HEAD)
CACHED_HASH=$(cat "$DB_DIR/.commit-hash" 2>/dev/null || echo "")
if [ "$CURRENT_HASH" = "$CACHED_HASH" ] \
&& [ -f "$DB_DIR/codeql-database.yml" ] \
&& [ -d "$DB_DIR/db-$LANG" ]; then
# Belt-and-suspenders: manifest yml + per-language db dir. Catches
# partial-write corruption from a prior crashed `codeql database create`.
echo "Reusing cached CodeQL database (commit $CURRENT_HASH)"
else
mkdir -p "$DB_DIR"
# exemplo JS/TS — adaptar --command para Java/C/etc:
codeql database create "$DB_DIR" \
--language="$LANG" \
--source-root=. \
--overwrite
# Persistir hash apenas apos build bem-sucedido
echo "$CURRENT_HASH" > "$DB_DIR/.commit-hash"
fi
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.
- 9d ago First seen · 179 lines · 90 tokens per session scan A 9b713bd97436
codeql-runner is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,660 once invoked, about $0.0005 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.