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/helix-parallel)<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/helix-parallel"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/helix-parallel/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/helix-parallel"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/helix-parallel.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 | $0.00013 | $0.02669 |
| Opus 5 | $0.00006 | $0.01334 |
| Sonnet 5 | $0.00003 | $0.00534 |
| Haiku 4.5 | $0.00001 | $0.00267 |
Grade A, and why
helix-parallel 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helix Parallel Research
⚠️ DEPRECADO (v6.2): Este command é mantido para compatibilidade. USE:
audience-research-agentcomo entry point único para pesquisa. Ver~/.claude/WORKFLOW-CANONICO.mdpara o fluxo recomendado.Quando usar este command:
- Casos específicos onde você precisa controle granular sobre os 4 tasks
- Debugging de módulos individuais
- Para todos os outros casos, use
audience-research-agent
Execute parallel research for offer: $ARGUMENTS
IMPORTANTE (v4.3): Todos os tasks usam
subagent_type: general-purposepara garantir acesso aos MCPs (Apify, Firecrawl, Playwright). Custom types comoresearcherNÃO herdam MCPs.
Extended Thinking Bifásica (v6.1) ⚠️ NOVO
Fonte:
~/.claude/rules/briefings-helix.mdv6.1
| Fase Research | Extended Thinking | Budget |
|---|---|---|
| VOC Research | ON | 10-16K |
| Competitor Analysis | ON | 10-16K |
| Mechanism Research | ON | 10-16K |
| Avatar Profiling | ON | 10-16K |
| Synthesis | ON | 10-16K |
Todos os tasks de research usam Extended Thinking ON para análise profunda.
Templates Disponíveis (v6.1)
Para fases posteriores (HELIX briefing), usar:
~/.claude/templates/mup-mus-discovery.md→ Fases 5-6 (MUP/MUS)~/.claude/templates/rmbc-ii-workflow.md→ Fases 7-10 (VSL structure)
Pre-Flight Check
Before starting, verify:
# 1. Check offer directory exists
ls ~/copywriting-ecosystem/*/$ARGUMENTS/ 2>/dev/null || echo "CREATE DIRECTORY FIRST"
# 2. Check task_plan.md exists
cat ~/copywriting-ecosystem/*/$ARGUMENTS/task_plan.md 2>/dev/null || echo "RUN /plan FIRST"
If directory doesn't exist, create it:
~/copywriting-ecosystem/create-offer.sh "[nicho]" "$ARGUMENTS"
Create Research Subdirectories
mkdir -p research/$ARGUMENTS/{voc,competitors,mechanism,avatar}/{raw,processed}
Parallel Execution (Fan-out)
Launch 4 research tasks SIMULTANEOUSLY:
Task 1: VOC Research
Use Task tool with subagent_type: general-purpose
PROMPT:
"Você é um specialist em VOC extraction para copywriting de Direct Response.
OFFER: $ARGUMENTS
FERRAMENTAS DISPONÍVEIS (USAR OBRIGATORIAMENTE):
- mcp__apify (YouTube, Instagram, TikTok comments)
- mcp__firecrawl (landing pages, reviews)
- mcp__playwright (Meta Ads Library, sites com login)
VOC QUALITY PROTOCOL:
1. Apify Actor específico PRIMEIRO
2. Playwright se Apify falha
3. Firecrawl se Playwright falha
4. WebSearch APENAS como ÚLTIMO RESORT
TAREFA: Extrair VOC autêntico de YouTube, Instagram, TikTok, Reclame Aqui, Mercado Livre
OUTPUT: research/$ARGUMENTS/voc/
FOCO: Pain points (viscerais), desires, objections, language patterns verbatim
LIMITE: 100 quotes por plataforma
ESTRUTURA:
- raw/ → dados brutos por fonte
- processed/ → pain-points.md, desires.md, objections.md, language-patterns.md
- summary.md → ≤500 tokens com key findings
"
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 · 335 lines · 13 tokens per session scan A 3ece798c63a3
helix-parallel is a command published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 2,669 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 2026-08-31.
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.