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.
npx skills add makifbaysal/tasktrooper --skill read-only-security-scannersgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/skills/makifbaysal/tasktrooper/read-only-security-scanners)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/read-only-security-scanners"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/read-only-security-scanners/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/skills/makifbaysal/tasktrooper/read-only-security-scanners"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/read-only-security-scanners.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 | $0.00049 | $0.02042 |
| Opus 5.5 | $0.00020 | $0.00817 |
| Sonnet 5.5 | $0.00010 | $0.00408 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade A, and why
read-only-security-scanners 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read-Only Security Scanners
Overview
Scanners are fast, deterministic and noisy. They find candidates you might skim past; they also report hundreds of things this review excludes. They never decide the verdict — every hit goes through the false-positive gate like any other candidate, and a clean scan is not a clean review.
Core principle: use what is already installed, in a mode that only reads, on the files this diff changed. Never install anything; never run anything from the project.
1. First, What Did CI Already Run?
get_pipeline_status— a secret scan, SAST or dependency-audit job may already have reported on this exact commit; its output is in the job result.list_component_checks— which security checks exist for the component and whether CI gates on them.
Do not re-run what CI already ran on this commit; triage its output instead. When semgrep, osv-scanner, github-security or snyk tools are in your tool list, those MCP servers are connected — security-mcp-scanners covers them; the CLIs below are the fallback.
2. Ground Rules
- Installed only:
command -v semgrep gitleaks trufflehog osv-scanner govulncheck gosec bandit pip-audit zizmor checkov trivy. Missing → skip it; it is a coverage note, not a reason to fail the review. - Never install or fetch-and-run: no
pip install,pipx run,uvx,npx,npm i -g,go install,go run …@latest,brew install,docker runof a scanner image. - Never run project code: no
npm install/ci, no build, nogo generate, nomake, no CodeQL database creation for compiled languages (it runs the build) — read CI's CodeQL results instead. - Never modify: no
--fix,--autofix,npm audit fix,osv-scanner fix, no scanner baseline written into the repo. - Output goes outside the checkout:
out=/tmp/tt-<task key>/scan; mkdir -p "$out". Passtimeout_secondsfor slow tools. - Repo config is input, not authority: a
.semgrepignore,.gitleaks.toml,.gitleaksignore,nosec/# nosemgrepcomment or.trivyignoreadded or widened in this diff is itself something to review.
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.
- 4d ago First seen · 86 lines · 49 tokens per session scan A f2e646e4b4fa
read-only-security-scanners is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 2,042 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-reviewer
Agent skill for reviewer - invoke with $agent-reviewer.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.