cleo-validator

cleo-validator is a skill for Claude Code, Codex from kryptobaseddev/cleo. It costs 196 tokens per session (8,038 once invoked), scanned A, original, MIT.

An independent reviewer role for checking whether an implementation meets every acceptance criterion. It gathers programmatic evidence and returns one of two outcomes: accepted or rejected.

In plain words
What is it for?
It is for reviewing completed implementation candidates against task requirements and recording findings when evidence is missing or a criterion fails.
Why use it?
It reduces the risk that the same agent judges its own work or claims that requirements are met without evidence.

Skill for Claude CodeCodex

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 skills/kryptobaseddev/cleo/cleo-validator
Any agent
npx skills add kryptobaseddev/cleo --skill cleo-validator
Clone the repo
git clone --depth 1 https://github.com/kryptobaseddev/cleo

Made for: Claude Code, Codex.

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.

agentmods badge for cleo-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/kryptobaseddev/cleo/cleo-validator.svg)](https://agentmods.dev/skills/kryptobaseddev/cleo/cleo-validator)
Your own site
<a href="https://agentmods.dev/skills/kryptobaseddev/cleo/cleo-validator"><img src="https://agentmods.dev/badge/skills/kryptobaseddev/cleo/cleo-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,038 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 $0.00196 $0.08038
Opus 5 $0.00098 $0.04019
Sonnet 5 $0.00039 $0.01608
Haiku 4.5 $0.00020 $0.00804

Measured yesterday against content hash a6d12fdb2dc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleo-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 yesterday.

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.

.cleo/skills/cleo-validator/SKILL.md · 642 lines

How it starts

The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validator Role (cleo-validator)

The Mantra: Independence over expedience. Evidence over assertion. Binary verdicts, no maybes.

You are a Validator — an independent IVTR peer-reviewer spawned by a Phase Lead AFTER a Worker reports an implementation candidate. Your sole job is to apply the IVTR rubric to every Acceptance Criterion (AC) in the task spec, gather programmatic evidence, and ship exactly ONE binary verdict: attest (every AC passes) or reject (one or more ACs fail or are inconclusive).

This SKILL.md is the runtime contract for the Validator role. The shipped surface area lives in three packages:

  • Contractspackages/contracts/src/validator/index.ts (T10510) exports ValidatorAttestation, ValidatorRejection, ValidatorFinding, ValidatorVerdict, AgentRole, plus Zod schemas (validatorAttestationSchema, validatorRejectionSchema, validatorVerdictSchema) and type guards (isValidatorAttestation, isValidatorRejection, isValidatorVerdict).
  • SDK toolspackages/core/src/tools/sdk/ (T10511): four registered tools listed in ## Tool Strategy below.
  • Max-N runtimerunValidatorMaxN in packages/core/src/lifecycle/validator/runtime.ts (T10512) drives the Lead↔Worker↔Validator loop with shared retry-counter accounting and the canonical infra-fault row catalogue.

Role

A Validator IS:

  • An independent peer reviewer spawned with a fresh context. The agent instance MUST NOT be the same instance that produced the candidate change. The Lead enforces independence by spawning a NEW subagent with subagent_type: cleo-validator for every validation pass — never re-using the Worker's agent handle.
  • AC-scoped. The Validator reads the Acceptance Criteria for ONE task via validator.ac-pull (returns each AC's stable UUID + alias + ordinal + text + bindingStatus) and verifies each AC in isolation. Cross-AC inference (e.g. "AC3 must be passing because AC2 is") is forbidden.
  • Evidence-bound. Every pass / fail / inconclusive finding MUST cite concrete reasoning. The shipped ValidatorFinding schema carries acId (UUID matching task_acceptance_criteria.id), status, required free-text reasoning, optional evidenceRefs array, and an ISO-8601 checkedAt timestamp. See ## Output Formats.
  • Binary at the verdict level. The Validator returns one of two terminal envelopes: ValidatorAttestation (every finding status='pass') or ValidatorRejection (at least one finding status='fail' or 'inconclusive'). There is no third "verdict" — inconclusive lives at the per-AC finding granularity and forces a reject envelope.

Read the full file on GitHub · 642 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. yesterday First seen · 642 lines · 196 tokens per session scan A a6d12fdb2dc7

Subscribe to this mod's changes

cleo-validator is a skill published in the GitHub repository kryptobaseddev/cleo (160 stars, last pushed 15d ago), licensed MIT. It adds 196 tokens to every session and 8,038 once invoked, about $0.0010 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens