Agent Output Verifier
Use when agent-produced work needs a safety, evidence, and reliability check before handoff, merge, or trust.
Install
npx skills add rohitg00/agentbrain --skill agent-output-verifiergit clone --depth 1 https://github.com/rohitg00/agentbrain.git /tmp/agentbrain
mkdir -p ~/.claude/skills
cp -r /tmp/agentbrain/skills/agent-output-verifier ~/.claude/skills/agent-output-verifierPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# agent-output-verifier Lifecycle stage: REVIEW ## Trigger Use before trusting or handing off output produced by an autonomous or semi-autonomous agent, especially after long-running work, tool use, code generation, external calls, or multi-step planning. Do not use as a replacement for domain review. This skill decides whether the output is safe and evidenced enough to enter the next review gate. ## When not to use Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate. ## Inputs - Agent output or artifact. - Original user request and constraints. - Tool logs, test logs, diffs, screenshots, traces, or citations. - List of tools the agent claimed to use. - Allowed scope, files, commands, and side effects. - Known secrets, private paths, or data classes that must not appear. ## Procedure 1. Restate the claimed outcome in one sentence. 2. Check for secret leakage: credentials, tokens, private URLs, keys, personal data, or connection strings. 3. Check for hallucinated tools or evidence: claimed commands, tests, APIs, files, screenshots, or links that have no supporting proof. 4. Check for unbounded loops: retry loops, background jobs, recursive scheduling, polling, or autonomous goals without stop conditions. 5. Check for skipped gates: tests not run, validation missing, review bypassed, user approval omitted, or destructive actions performed silently.
Details
- Skill name
agent-output-verifier- Repository
- rohitg00/agentbrain
- Path
skills/agent-output-verifier/SKILL.md- License
- MIT
- Repo updated
- 26 May 2026
FAQ
What does the Agent Output Verifier skill do?
Use when agent-produced work needs a safety, evidence, and reliability check before handoff, merge, or trust.
How do I install the Agent Output Verifier skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add rohitg00/agentbrain --skill agent-output-verifier. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Output Verifier popular?
It lives in rohitg00/agentbrain, which has 43 GitHub stars and 9 forks.
Related skills
Activity Recap
43rohitg00/agentbrain
Use when the user needs a standup-ready summary of recent project activity from local evidence.
Adapter Capability Probe
43rohitg00/agentbrain
Use when a command, adapter, or runtime smoke depends on proving an agent runtime's capabilities before trusting command routing, writes, shell access, or validation claims.
Artifact Contract
43rohitg00/agentbrain
Use when an output artifact, template, schema, example, or handoff field must stay aligned across commands, skills, docs, and validators.
Brain Eval
43rohitg00/agentbrain
Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.
Trellis Review Twostage
44coldwateryi/trellis-skills
Before marking a Trellis subtask complete after self-check all green, conduct two-stage code review: mechanically check spec compliance (against PRD acceptance criteria/decision table/forbidden/file manifest/mount points), then code quality review (against .trellis/spec/guides engineering standards and design discipline). Used in Codex / Claude Code team collaboration scenarios, especially when implementation is by a small-parameter model like qwen3.6 35b—small models reviewing their own code is unreliable, Stage 2 should escalate to strong model; critical issues block completion.
Brain Grill
43rohitg00/agentbrain
Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.