An adversarial review skill for challenging strategic copy decisions, such as a unique selling idea, central belief, mechanism, or hook.

Use it to stress-test copy strategy and receive a verdict of stand, revise, or escalate with the main issues and recommendation.

It provides a deliberate second opinion that looks for unsupported assumptions and weaknesses before an idea is used in production.

copy-critic — Skill for Claude Code and Codex by lckx777

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.

Any agent

npx skills add lckx777/copy-chief-black --skill copy-critic

Clone the repo

git clone --depth 1 https://github.com/lckx777/copy-chief-black

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lckx777/copy-chief-black/copy-critic/github.svg)](https://agentmods.dev/skills/lckx777/copy-chief-black/copy-critic)

Your own site

<a href="https://agentmods.dev/skills/lckx777/copy-chief-black/copy-critic"><img src="https://agentmods.dev/badge/skills/lckx777/copy-chief-black/copy-critic/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/skills/lckx777/copy-chief-black/copy-critic"><img src="https://agentmods.dev/badge/skills/lckx777/copy-chief-black/copy-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,908 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	$0.00058	$0.05908
Opus 5	$0.00029	$0.02954
Sonnet 5	$0.00012	$0.01182
Haiku 4.5	$0.00006	$0.00591

Measured 9d ago against content hash ada7ee3468a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

copy-critic 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 9d 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.

framework/skills/copy-critic/SKILL.md · 685 lines

How it starts

The opening of the file, as written. The whole thing — 685 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copy Critic

Crítico adversarial que força análise rigorosa de decisões de copy.

Anti-sycophancy: NÃO valida, DESAFIA.

Quick Start

Receber decisão/claim a testar (MUP, MUS, One Belief, hook, etc.)
Executar 5 fases de análise (4 adversarial + 1 multi-modelo)
Entregar verdict com recomendação → Output: STAND / REVISE / ESCALATE + claims testadas + zen_scores (v4.6)

Output Location

Write all outputs to:

Validation reports: briefings/{offer-name}/validations/{type}-{date}.md
Summary in chat (short verdict + key issues)

Structure:

briefings/{offer}/validations/
├── mup-validation-2026-01-14.md
├── mus-validation-2026-01-14.md
├── onebelief-validation-2026-01-14.md
└── hook-validation-2026-01-14.md

CRITICAL: Always save full analysis to file. Return only summary to chat:

Verdict: STAND/REVISE/ESCALATE
Confidence: X%
Key issues (if any)
Recommendation

Workflow (5 Fases)

Fase 1: DECOMPOSE

Extrair e classificar elementos da decisão:

claims:
  - id: C1
    statement: "[claim extraída]"
    type: factual|analytical|predictive

assumptions:
  - id: A1
    statement: "[assumption implícita]"
    risk: low|medium|high

constraints:
  - id: K1
    statement: "[constraint identificada]"

Fase 2: VERIFY

Para cada claim importante:

Gerar pergunta de verificação
Responder INDEPENDENTEMENTE (sem viés de confirmação)
Marcar status: VERIFIED | UNCERTAIN | FAILED

Fase 3: CHALLENGE

Steel-man argument CONTRA a decisão:

"E se o oposto for verdade?"
"Qual o pior cenário?"
"O que o concorrente mais forte faria diferente?"
"Isso funcionaria para um público diferente?"
"Que evidência me faria mudar de ideia?"

Fase 4: SYNTHESIZE

verdict: STAND | REVISE | ESCALATE
confidence: [0-100]%
failed_items: [lista de C/A que falharam]
uncertain_items: [lista de C/A incertos]
recommendation: "[ação específica]"

Fase 4.5: COGNITIVE-AFFECTIVE GAP + BLACK ENFORCEMENT (v6.3) ⚠️ ATUALIZADO

Read the full file on GitHub · 685 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 685 lines · 58 tokens per session scan A ada7ee3468a1

Subscribe to this mod's changes

copy-critic is a skill published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 5,908 once invoked, about $0.0003 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.

Code review Marketing and SEO

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens