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 security-mcp-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/security-mcp-scanners)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/security-mcp-scanners"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/security-mcp-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/security-mcp-scanners"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/security-mcp-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 | $0.00053 | $0.01602 |
| Opus 5.5 | $0.00021 | $0.00641 |
| Sonnet 5.5 | $0.00011 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
security-mcp-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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security MCP Scanners
Overview
Four security MCP servers can be connected for you: semgrep, osv-scanner, github-security and snyk. They ship disabled; the user turns them on in Settings → MCP servers. Your policy allows these four and no other server — a reviewer never holds the mutating MCP tools (Unity, Blender, Jupyter …) that other agents may use.
Core principle: an MCP scanner is a scanner. Its output is a list of candidates for the false-positive gate, never the verdict — and a scanner that failed is never a clean result.
1. Is It Connected?
- Availability is decided by your tool list, nothing else: tools from the
semgrepserver (namedmcp__semgrep__…in CLI runtimes),osv-scanner,github-security,snyk. Not in the list → the server is not enabled; do not try to call it, do not ask for it, fall back to installed CLIs (read-only-security-scanners) and to reading. - A listed tool that errors, times out, fails authentication or returns a parse error → a coverage limit for your summary line ("osv-scanner MCP: auth failed — lockfile not scanned"). Never treat it as "no findings".
- Order:
get_pipeline_statusfirst (CI may already have scanned this commit), thengithub-security(alerts GitHub already computed), then local scans (semgrep,osv-scanner), thensnykonly when it adds coverage the others do not.
2. semgrep — local SAST
The official semgrep mcp server, started with metrics off. Code is scanned on this machine.
- Scan the changed files, not the repository.
- Pass rule packs explicitly:
p/default,p/owasp-top-ten,p/secrets, plus the language pack for the stack (p/golang,p/java,p/python,p/typescript…). Neverauto— it requires metrics and sends project information. - The custom-rule tool is useful for a hypothesis: write a narrow rule that finds every call of the sink you suspect, or every sibling handler without the auth middleware. That is reading, and often faster than grep across languages.
- With a platform token configured, its findings tools show existing Semgrep platform results — read them like CI output.
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 · 84 lines · 53 tokens per session scan A 126dffe6d627
security-mcp-scanners is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 1,602 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.