Borrowing it
Nothing to install: this file belongs to AgentSafe-AI/tooltrust-scanner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/.agents/skills/verify-tooltrust-scanner/SKILL.mdgit clone --depth 1 https://github.com/AgentSafe-AI/tooltrust-scannerWrote 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/agentsafe-ai/tooltrust-scanner/verify-tooltrust-scanner)<a href="https://agentmods.dev/skills/agentsafe-ai/tooltrust-scanner/verify-tooltrust-scanner"><img src="https://agentmods.dev/badge/skills/agentsafe-ai/tooltrust-scanner/verify-tooltrust-scanner/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/agentsafe-ai/tooltrust-scanner/verify-tooltrust-scanner"><img src="https://agentmods.dev/badge/skills/agentsafe-ai/tooltrust-scanner/verify-tooltrust-scanner.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 | $0.00052 | $0.01712 |
| Opus 5.5 | $0.00021 | $0.00685 |
| Sonnet 5.5 | $0.00010 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
verify-tooltrust-scanner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify ToolTrust Scanner
Read features/README.md first. This is a project-local verification skill for the Go scanner repository, not the separate ToolTrust Directory publisher. It drives compiled binaries through their public command line and JSON-RPC stdio interfaces. It does not change production code or run third-party MCP packages.
Launch
Requirements: macOS or Linux, Python 3.9+ with its standard library, Git, and Go capable of using the toolchain in go.mod (currently Go 1.26.9). Initial builds may download that toolchain and modules. The checkout must build as-is. If it fails, preserve build logs and report the blocker; do not substitute a previously installed scanner.
Run from the scanner repository root:
TT_VERIFY_RUN="$(mktemp -d /tmp/tooltrust-verify.XXXXXX)/run"
python3 .agents/skills/verify-tooltrust-scanner/scripts/verify.py launch --run "$TT_VERIFY_RUN"
python3 .agents/skills/verify-tooltrust-scanner/scripts/verify.py doctor --run "$TT_VERIFY_RUN"
launch builds tooltrust-scanner and tooltrust-mcp into the unique run's runtime/bin/, with a version containing the Git revision and source fingerprint. Readiness is both version commands returning that value and matching binary hashes. This is a short-lived CLI/stdio application: no user login or persistent service is needed. The optional osv drive starts and closes an owned loopback HTTP listener on an ephemeral port.
Every drive gets a new subprocess/process group and uses the run's scratch working directory. Runs can coexist if their --run paths differ. Never reuse another agent's run, binaries, PID, working directory or config. Never point these commands at the user's real MCP configuration.
Doctor
python3 .agents/skills/verify-tooltrust-scanner/scripts/verify.py doctor --run "$TT_VERIFY_RUN"
This reads source/fixture/helper fingerprints and binary hashes and invokes read-only version commands. It writes only evidence transcripts. If source, fixture or helper code changed, launch a fresh run; a build of old code cannot prove a new change. After cleanup, doctor should fail because the binaries have been removed.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- acceptance.md 3.8 KB
- features/gate.md 1.7 KB
- features/live.md 1.8 KB
- features/mcp.md 1.7 KB
- features/osv.md 985 B
- features/README.md 2.2 KB
- features/release.md 1.6 KB
- features/source.md 2.1 KB
- features/static.md 1.9 KB
- fixtures/tools.json 538 B
- repair-verification-result.json 3.5 KB
- scripts/fixture_server.py 1.5 KB runs code
- scripts/verify.py 27 KB runs code
- verification-result.json 2.6 KB
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.
- 14d ago Changed · +4 lines 0f4fc556e49a
- 15d ago First seen · 84 lines · 52 tokens per session scan A 6dd7dd439757
verify-tooltrust-scanner is a skill published in the GitHub repository AgentSafe-AI/tooltrust-scanner (19 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,712 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 2026-10-13.
Other skills, from other repositories
terraform-skill
Terraform infrastructure as code best practices.
playwright-skill
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.
testing-llm-prompt-injection-and-jailbreaks
Testing LLM-backed applications, chatbots, and AI agents for direct and indirect prompt injection, jailbreaks, system-prompt leakage, and tool/agent abuse during authorized penetration tests, using structured payload families and reliable confirmation signals.
pypict-skill
Pairwise test generation.
deploy-registry-server-with-otel
Deploy the ToolHive Registry Server to a Kind cluster with telemetry enabled. Use when you need to deploy the registry server for testing with OTEL metrics and tracing.
smoke-test
Start the Registry Server via docker compose and run a suite of curl-based smoke tests covering system, read-only MCP API, admin API, entry lifecycle, and OAuth/auth enforcement scenarios.