← Back to Skills Marketplace
Proof Agent
by
acolombiadev
· GitHub ↗
· v1.1.0
· MIT-0
159
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install proof-agent
Description
Adversarial verification of AI-generated work. Spawns an independent verifier to check for false claims, broken code, and security issues.
Usage Guidance
This skill appears to do what it says: build a verification prompt and run factual/build checks. Before using it, be aware that verification requires sharing the changed files and command outputs with a separate verifier agent — those can include sensitive data. Recommendations: (1) Inspect and redact any secrets in changed files before sending to an external verifier, (2) run the scripts locally in a sandboxed environment if you do not trust the verifier agent, and (3) treat the verifier's network commands' outputs as potentially exposing repository data (URL checks and registry queries are performed). If you need stronger guarantees, add automatic secret-redaction or limit which files are passed to the verifier.
Capability Analysis
Type: OpenClaw Skill
Name: proof-agent
Version: 1.1.0
The 'proof-agent' skill is a defensive utility designed to provide independent verification of AI-generated code changes. It includes 'scripts/verify.sh' to gather git context and 'scripts/fact-check.sh' to validate external references like URLs, npm packages, and GitHub Actions via curl. The behavior is well-documented, lacks obfuscation, and is strictly aligned with its stated purpose of identifying bugs and security vulnerabilities in a multi-agent workflow.
Capability Assessment
Purpose & Capability
The name/description (adversarial verification) matches the included files and instructions: scripts extract git diffs, detect sensitive filenames, run URL/npm/GitHub/PyPI checks, and build a verification prompt for a separate verifier. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
SKILL.md narrowly defines what to give the verifier (original request, changed files, approach) and requires the verifier to run commands and include outputs. This is coherent for verification. However, the workflow shares changed files and command outputs with a separate agent; if changed files contain secrets the verifier would receive them unless the caller redacts them. The provided scripts detect sensitive filename patterns but do not automatically redact secret contents.
Install Mechanism
Instruction-only skill with small shell scripts; no install spec, no archives, no remote installers. This is low-risk from an install standpoint.
Credentials
No environment variables, credentials, or system config paths are requested. The scripts perform network queries (curl to URLs, npm registry, GitHub) which is appropriate for fact-checking and consistent with the stated purpose.
Persistence & Privilege
Skill is not always-enabled and does not request persistent system privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install proof-agent - After installation, invoke the skill by name or use
/proof-agent - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Updated README with collapsible sections for better scannability. Added details tags for advanced configuration and troubleshooting while maintaining all content.
v1.0.1
Clean repo rebuild: removed dead code (ReportingConfig, commands_run), fixed entrypoint verdict parsing (structured headings only), added gh copilot availability check, printf portability fix
v1.0.0
Independent adversarial verification for AI-generated work — spawns a separate verifier agent that checks code, facts, and security with its own commands
Metadata
Frequently Asked Questions
What is Proof Agent?
Adversarial verification of AI-generated work. Spawns an independent verifier to check for false claims, broken code, and security issues. It is an AI Agent Skill for Claude Code / OpenClaw, with 159 downloads so far.
How do I install Proof Agent?
Run "/install proof-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Proof Agent free?
Yes, Proof Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Proof Agent support?
Proof Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Proof Agent?
It is built and maintained by acolombiadev (@andreagriffiths11); the current version is v1.1.0.
More Skills