Auditing agent actions
Skill casioreview20-glitch/forge-os/skills-v2/kernel/auditing-agent-actions
The open-source control plane for AI agents — skill routing, context governance, trustworthy execution, evidence, security, and multi-agent orchestration.
npx -y skills add casioreview20-glitch/forge-os --skill auditing-agent-actionsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 10 days oldThe repository was created 10 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when model decisions, tool calls, approvals, artifact mutations, provider selections, or evidence issuance must be reconstructed without storing secrets or unverifiable narrative.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
0.9 KB, as published. Nobody here has run it
Auditing Agent Actions
Core principle
Assign request, route, context, run, tool, evidence, and gate correlation IDs. Expose bounded query views without leaking protected payloads. The runtime owns deterministic scope, coverage, policy, and evidence checks; the agent owns only the judgment that cannot be reduced safely to code.
Do not activate when
- high-volume debug telemetry with no audit value
- raw secret-bearing payloads that policy forbids storing