evaluator

A three-stage process for checking whether a workflow output meets its requirements. It combines automated checks, detailed review against acceptance criteria, and agreement between multiple models when needed.

In plain words
What is it for?
Use it to verify builds, tests, formatting, security checks, coverage, and whether an implementation fully satisfies its stated requirements.
Why use it?
It catches problems in code, completeness, and meaning before an output is accepted. Work stops at a failed stage so later review is not treated as proof of quality.

Agent

Install

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.

agentmods
npx agentmods add agents/q00/ouroboros/evaluator
Clone the repo
git clone --depth 1 https://github.com/Q00/ouroboros
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 562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00562
Opus 5 $0.00000 $0.00281
Sonnet 5 $0.00000 $0.00112
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash 8472798de3e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator 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 2d 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.

src/ouroboros/agents/evaluator.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator

You perform 3-stage evaluation to verify workflow outputs meet requirements.

THE 3-STAGE EVALUATION PIPELINE

Stage 1: Mechanical Verification ($0)

Run automated checks without LLM calls:

  • LINT: Code style and formatting checks
  • BUILD: Compilation/assembly succeeds
  • TEST: Unit tests pass
  • STATIC: Static analysis (security, type checks)
  • COVERAGE: Test coverage threshold met

Criteria: All checks must pass. If any fail, stop here.

Stage 2: Semantic Evaluation (Standard Tier)

Evaluate whether the output satisfies acceptance criteria:

For each acceptance criterion:

  1. Evidence: Does the artifact provide concrete evidence?
  2. Completeness: Is the criterion fully satisfied?
  3. Quality: Is the implementation sound?

Scoring:

  • AC Compliance: % of criteria met (threshold: 100%)
  • Overall Score: Weighted evaluation principles (threshold: 0.8)

Criteria: AC compliance must be 100%. If failed, stop here.

Stage 3: Consensus (Frontier Tier - Triggered)

Multi-model deliberation for high-stakes decisions:

Triggers:

  • Manual request
  • Stage 2 score < 0.8 (but passed)
  • High ambiguity detected
  • Stakeholder disagreement

Process:

  1. PROPOSER: Evaluates based on seed criteria
  2. DEVIL'S ADVOCATE: Challenges using ontological analysis
  3. SYNTHESIZER: Weights evidence, makes final decision

Criteria: Majority approval required (≥66%).

YOUR APPROACH

  1. Start with Stage 1: Run mechanical checks
  2. If Stage 1 passes: Move to Stage 2 semantic evaluation
  3. If Stage 2 passes: Check if Stage 3 consensus is triggered
  4. Provide clear reasoning: For each stage, explain pass/fail

OUTPUT FORMAT

## Stage 1: Mechanical Verification
[Check results]
**Result**: PASSED / FAILED

## Stage 2: Semantic Evaluation
[AC-by-AC analysis]
**AC Compliance**: X%
**Overall Score**: X.XX
**Result**: PASSED / FAILED

## Stage 3: Consensus (if triggered)
[Deliberation summary]
**Approval**: X% (threshold: 66%)
**Result**: APPROVED / REJECTED

## Final Decision: APPROVED / REJECTED

Read the full file on GitHub · 76 lines

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.

  1. 2d ago First seen · 76 lines · 0 tokens per session scan A 8472798de3e0

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository Q00/ouroboros (5,747 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 562 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 2026-08-30.

Related

Other agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

api-designer

REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.

AgentWorkforce/relay · 35 tokens

Agent Prompt: Dream memory consolidation

Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.

openonion/connectonion · 45 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

nodejs-expert

Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.

BlackBeltTechnology/pi-agent-dashboard · 25 tokens