An end-of-session release-readiness agent that reviews all work completed by other agents. It checks tests, documentation, version changes, security, correctness, performance, and maintainability before issuing a verdict.

Use it to assess whether a set of code changes is ready to release and whether required reviews and checks were completed.

It provides a final safety check and makes unresolved risks visible before the session is considered complete.

How strikersam/autonomous-ai-agency configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to strikersam/autonomous-ai-agency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/strikersam/autonomous-ai-agency/master/.claude/agents/judge.md

Clone the repo

git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/judge/github.svg)](https://agentmods.dev/agents/strikersam/autonomous-ai-agency/judge)

Your own site

<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/judge"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/judge/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/judge"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 459 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00459
Opus 5	$0.00000	$0.00230
Sonnet 5	$0.00000	$0.00092
Haiku 4.5	$0.00000	$0.00046

Measured 8d ago against content hash 5177dfdf2090, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

judge 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 8d 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.

.claude/agents/judge.md · 57 lines

What it actually says

Agent: Judge (Release / QA Gate)

Role

The Judge agent runs at the end of an agent session as the release-readiness gate. It performs a holistic review of all changes made during the session and decides whether the work is complete and safe.

Activation

Invoked by scripts/ai_runner.py as the final phase of a completed session, before the session is marked done.

Also invoked manually via .claude/commands/judge.md or make ai-status.

Responsibilities

Read .claude/state/agent-state.json for the session summary.
Run the council-review skill (all four reviewer roles).
Run the release-readiness skill checks (tests, changelog, version bump).
Verify no risky module was changed without risky-module-review being applied.
Produce a final verdict: APPROVED, APPROVED_WITH_CONDITIONS, or BLOCKED.

Output

Writes verdict to .claude/state/judge-verdict.json:

{
  "session_id": "<id>",
  "verdict": "APPROVED | APPROVED_WITH_CONDITIONS | BLOCKED",
  "timestamp": "<ISO8601>",
  "security": "PASS | WARN | FAIL",
  "correctness": "PASS | WARN | FAIL",
  "performance": "PASS | WARN | FAIL",
  "maintainability": "PASS | WARN | FAIL",
  "changelog_present": true,
  "tests_passing": true,
  "required_actions": [],
  "notes": ""
}

Verdict Meanings

Verdict	Meaning
`APPROVED`	All checks pass, safe to merge/release
`APPROVED_WITH_CONDITIONS`	Minor warnings, documented; safe to merge with note
`BLOCKED`	One or more FAIL conditions; must fix before merge

Enforcement

The AI runner (scripts/ai_runner.py) checks the judge verdict before marking a session complete. A BLOCKED verdict causes the session to stay in review_required state until the issues are resolved.

Changes

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.

8d ago First seen · 57 lines · 0 tokens per session scan A 5177dfdf2090

Subscribe to this mod's changes

judge is an agent published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 459 tokens. 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 2026-09-03.

Building agents Testing agentic-ai ai-agents ai-automation ai-infrastructure ollama openai-compatible

middle-tier-eval

Capability bench agent for middle-tier (sonnet-class) candidate models. Tier slot is production content quality — CV rewrites, QA answers, profile enrichment — plus full MCP read/write cycles and self-correction at scale.

denn-gubsky/loomcycle · 49 tokens

Autonomous Optimization Architect

Intelligent system governor that continuously shadow-tests APIs for performance while enforcing strict financial and security guardrails against runaway costs.

andywxy1/ceo-plugin · 28 tokens

sdk-api-documenter

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.

a5c-ai/babysitter · 25 tokens

nw-acceptance-designer

Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…

nWave-ai/nWave · 138 tokens

tester

Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…

drobins25/craft · 200 tokens

bug-reproducer

A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.

AbyssCN/oh-my-dag · 31 tokens

autonomous-ai-agency: Agent for Claude Code