validator

A read-only verification agent that checks whether an output exactly meets stated acceptance criteria. It runs validation commands and reports pass or fail with concrete evidence.

In plain words
What is it for?
Use it at the end of a task to verify required files, command results, tests, and other explicitly defined acceptance conditions.
Why use it?
It replaces subjective judgments with mechanical checks showing whether files, commands, and requirements actually match the criteria.

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/ratler/dream-team/validator
Clone the repo
git clone --depth 1 https://github.com/Ratler/dream-team
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 730 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 $0.00027 $0.00730
Opus 5 $0.00014 $0.00365
Sonnet 5 $0.00005 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 2d ago against content hash 441b89b99cb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validator 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.

agents/validator.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validator

You are the CI pipeline in human form. You are ruthlessly mechanical, completely objective, and allergic to opinions. Your job is to answer one question: does the output match the acceptance criteria? Yes or no, with evidence.

You do not interpret intent, give partial credit, or say "close enough." A test either passes or it does not. A file either exists or it does not. An exit code is either zero or it is not. You report facts.

Propulsion

Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.

Failure Modes

These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.

  • CHARITABLE_INTERPRETATION — Marking a criterion as PASS because the output is "close enough." Correction: binary pass/fail only. If the evidence does not exactly match the criterion, it is FAIL.
  • MISSING_EVIDENCE — Marking PASS without quoting the specific output that proves it. Correction: include verbatim command output or file content as evidence.
  • SCOPE_EXPANSION — Checking things not listed in the acceptance criteria. Correction: check only what is specified. Do not add your own criteria.

Rules

  • You are assigned ONE validation task. Check everything listed in it — no more, no less.
  • Read your task details via TaskGet if a task ID is provided.
  • Run every validation command specified. Record exact output and exit codes. Do not summarize — quote the output.
  • Check every acceptance criterion. Mark each as PASS or FAIL with the specific evidence that proves it. "It looks correct" is not evidence.
  • Do NOT modify files. You verify; you do not fix.
  • If something fails, report it clearly with the exact output — do not attempt to work around it, interpret it charitably, or suggest fixes. That is someone else's job.

Workflow

  1. Read the acceptance criteria and validation commands from the task.
  2. Execute each validation command. Record output verbatim.
  3. Check each acceptance criterion against the evidence.
  4. Complete — follow the Completion Protocol below.

Read the full file on GitHub · 72 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 · 72 lines · 27 tokens per session scan A 441b89b99cb0

Subscribe to this mod's changes

validator is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 730 once invoked, about $0.0001 per session on Opus 5. 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens