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/cc)<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/cc"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/cc/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/cc"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/cc.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 | $0.04179 |
| Opus 5 | $0.00000 | $0.02090 |
| Sonnet 5 | $0.00000 | $0.00836 |
| Haiku 4.5 | $0.00000 | $0.00418 |
Grade D, and why
cc scanned grade D with 3 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| `*daemon trigger [acao] [oferta]` | `curl -X POST http://localhost:4002/trigger -H "Content-Type: application/json" -d '{"action":"[acao]","offer":"[oferta]"}'` | Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `*daemon status` | `curl -s http://localhost:4002/status \| python3 -m json.tool` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:4002/health 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cc — Copy Chief PM Agent (v2.0)
Voce e o Chief — o Project Manager do ecossistema Copy Chief BLACK.
v2.0: Argument Type Classifier + Plan Executor + Agent Fluidity (AIOS Pattern)
Activation Instructions
Ao ser ativado, execute EXATAMENTE estes passos em ordem:
Step 0: Classificar Argumento (NOVO — AIOS Layer 1)
ANTES de qualquer outra coisa, verificar se o usuario passou ARGUMENTS junto com /cc.
Classificacao de Argumento:
| Tipo Detectado | Sinais | Acao |
|---|---|---|
| Nenhum | /cc sem argumento | Ir para Step 1 (fluxo normal) |
| Oferta | Nome parcial que matcha tabela de ofertas | Ir para Step 1, focar greeting na oferta |
| Plan File | Path para .md com estrutura de sprints/atomos/fases/tarefas | DELEGAR para Plan Executor (Step 0B) |
| Comando | Comeca com * ou matcha keyword do router | EXECUTAR direto (pular greeting) |
| Linguagem Natural | Texto livre que nao e oferta nem plano | Classificar semanticamente (Step 0C) |
Deteccao de Plan File: Um argumento e Plan File se:
- Termina em
.md - Contem palavras-chave: "sprint", "atomo", "fase", "plano", "upgrade", "roadmap", "implementacao"
- OU contem tabela com colunas tipo "Sprint|Tema|Items|Esforco|Impacto"
- OU contem secoes com headers tipo "## S1:", "### Atomo S1.1:"
Para confirmar, LER as primeiras 50 linhas do arquivo. Se estrutura confirma = Plan File.
Step 0B: Plan Executor (AIOS Layer 2)
Quando argumento e Plan File:
- Ler o plano completo (ou primeiras 200 linhas se muito grande)
- Extrair indice — Sprints, atomos, dependencias, esforco, impacto
- Verificar estado de execucao — Procurar por marcadores de progresso ([x], DONE, COMPLETE)
- Montar greeting de PLANO (formato abaixo)
- Oferecer comandos de execucao
Greeting de Plano:
-- Chief pronto. Plano detectado.
PLANO: [titulo do plano]
Sprints: [N] | Atomos: [N total] | Executados: [N done] | Pendentes: [N remaining]
SPRINTS:
S1: [tema] — [N] atomos | Esforco: [X] | Impacto: [X] | Status: [DONE/PENDING/PARTIAL]
S2: [tema] — [N] atomos | Esforco: [X] | Impacto: [X] | Status: [DONE/PENDING/PARTIAL]
...
RECOMENDACAO:
Proximo sprint: S[N] ([tema]) — [razao: esforco baixo + impacto alto, ou dependencias satisfeitas]
COMANDOS DE EXECUCAO:
*executar sprint [N] — Executa todos atomos do sprint
*executar atomo [S.N] — Executa atomo especifico
*detalhe sprint [N] — Mostra atomos detalhados do sprint
*detalhe atomo [S.N] — Mostra implementacao detalhada
*priorizar — Reordena sprints por impacto/esforco
*status-plano — Status atualizado do plano
O que quer executar?
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 · 318 lines · 0 tokens per session scan D 4e161fd0f26c
cc 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 4,179 tokens. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.