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 suyoumo/ClawProBench --skill local-testgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/local-test)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/local-test"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/local-test/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/suyoumo/clawprobench/local-test"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/local-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 34 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 69 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 78 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 88 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 98 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 108 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 131 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 132 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00022 | $0.01745 |
| Opus 5.5 | $0.00009 | $0.00698 |
| Sonnet 5.5 | $0.00004 | $0.00349 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
local-test 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 1mo 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Testing with Docker + Chrome MCP
Use this skill to build, run, and test IronClaw web gateway changes locally using Dockerfile.test and Chrome MCP browser automation tools.
Quick Start
# Build the test image (libsql-only, no PostgreSQL needed)
docker build --platform linux/amd64 -f Dockerfile.test -t ironclaw-test .
# Run on port 3003 (default)
docker run --rm -p 3003:3003 \
-e ONBOARD_COMPLETED=true \
-e CLI_ENABLED=false \
-e NEARAI_API_KEY=<key> \
ironclaw-test
# Open in browser
# http://localhost:3003/?token=test
Building the Image
The test Dockerfile uses a two-stage build: Rust compilation with --features libsql (no PostgreSQL dependency), then a minimal Debian runtime image.
docker build --platform linux/amd64 -f Dockerfile.test -t ironclaw-test .
Build takes ~5-10 minutes on first run (cached subsequent builds are faster). The --platform linux/amd64 flag avoids QEMU warnings on Apple Silicon but can be omitted if targeting native architecture.
Running Containers
Required Environment Variables
| Variable | Purpose | Default in Dockerfile |
|---|---|---|
ONBOARD_COMPLETED=true |
Skip onboarding wizard (exits immediately otherwise) | not set |
CLI_ENABLED=false |
Disable TUI/REPL (causes EOF shutdown otherwise) | not set |
LLM Backend Configuration
Pick ONE of these configurations:
NEAR AI (API key mode):
docker run --rm -p 3003:3003 \
-e ONBOARD_COMPLETED=true \
-e CLI_ENABLED=false \
-e NEARAI_API_KEY=<your-key> \
ironclaw-test
NEAR AI (session token mode):
docker run --rm -p 3003:3003 \
-e ONBOARD_COMPLETED=true \
-e CLI_ENABLED=false \
-e NEARAI_SESSION_TOKEN=<sess_xxx> \
-e NEARAI_BASE_URL=https://private.near.ai \
ironclaw-test
OpenAI:
docker run --rm -p 3003:3003 \
-e ONBOARD_COMPLETED=true \
-e CLI_ENABLED=false \
-e LLM_BACKEND=openai \
-e OPENAI_API_KEY=<your-key> \
ironclaw-test
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.
- 1mo ago First seen · 226 lines · 22 tokens per session scan A ecf08044ae9b
local-test is a skill published in the GitHub repository suyoumo/ClawProBench (827 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,745 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
githubsim
Test the GitHub App, repositories, pull requests and webhooks locally with githubsim, haven's GitHub stand-in: install page, installation tokens, scripted 401/403/404/422/429/5xx, signed webhooks, OAuth. Use when someone says 'haven github', 'githubsim', 'haven up +github', 'haven sim github', 'connect GitHub…
browser-test
Check that a feature works by walking its scenarios in a real browser and writing a pass/fail report with evidence. A recipe over haven browser: no test files, no browser commands of its own. Use when someone says 'browser test', 'verify this in the browser', 'walk the scenarios', 'check the feature live', or hands…
mfasim
Emulate second factors in a test browser: passkeys, security keys and U2F tokens through Chromium's virtual WebAuthn authenticators, and TOTP (authenticator app) codes typed without the agent ever seeing the secret. haven browser mfa on a haven browser lane, addVirtualAuthenticator in the Playwright e2e suites. Use…