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.
git clone --depth 1 https://github.com/lckx777/copy-chief-blackWrote 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.
[](https://agentmods.dev/commands/lckx777/copy-chief-black/expert)<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/expert"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/expert/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.
<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/expert"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00531 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
expert 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Chefe de Copy — the intelligent router that matches tasks to the best Copy Squad expert.
When the user provides a task and context, analyze the offer's CONTEXT.md to extract:
- Nicho (from directory structure)
- DRE (Dominant Resident Emotion from CONTEXT.md)
- Phase (from helix-state.yaml)
- Mecanismo state (from mecanismo-unico.yaml)
Then run the router:
bun run ~/.claude/scripts/chefe-de-copy.ts --task $ARGUMENTS --offer [detected-offer]
If no task is specified, show available tasks:
bun run ~/.claude/scripts/chefe-de-copy.ts --list-tasks
After showing the recommendation, load the Voice DNA of the recommended expert:
- Read the expert's profile from
~/.claude/copy-squad/{expert-name}.md - Summarize their core philosophy and voice patterns
- Suggest how to apply their approach to the current task
Format your response as:
- TOP 3 experts ranked with scores and reasons
- Voice DNA summary of #1 recommendation
- Practical application tips for the specific task
- APEX Fidelity Info: Show the expert's strong dimension and threshold from
~/.claude/rules/copy-fidelity.md
APEX Fidelity Score
After recommending an expert, also display their APEX fidelity requirements:
- Strong Dimension: The dimension where this expert MUST score high (from
~/.claude/experts/fidelity/apex-prompts.yaml) - Threshold: Minimum score required for that dimension
- Techniques: Key techniques that MUST be present in the output
This ensures the producer knows WHAT to focus on for faithful reproduction of the expert's style.
Run bun run scripts/fidelity-score.ts --list to show all expert thresholds.
Discovery Mode (Low Score Detection)
If the TOP expert scores below 60, activate Discovery Mode:
- Inform the user: "Nenhum expert atual tem score ideal para [task]. Score maximo: [score]/100."
- Use WebSearch to find:
"best copywriter for [task type]" - Suggest: "O expert ideal para [task] seria [name]. Use
/clone-expert [name]para clonar a mente dele para o Copy Squad." - Still show the TOP 3 from existing experts as fallback.
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 · 50 lines · 0 tokens per session scan A 64d6af737f9b
expert is a command published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 531 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.