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.
npx skills add JotJunior/cstk --skill agente-00cgit clone --depth 1 https://github.com/JotJunior/cstkWrote 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/skills/jotjunior/cstk/agente-00c)<a href="https://agentmods.dev/skills/jotjunior/cstk/agente-00c"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/agente-00c/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/skills/jotjunior/cstk/agente-00c"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/agente-00c.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 | $0.00034 | $0.00800 |
| Opus 5.5 | $0.00014 | $0.00320 |
| Sonnet 5.5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
agente-00c 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 10d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline de projeto no Codex
Leia primeiro ../feature-00c/SKILL.md para os contratos de segurança,
decisões, evidências, lock, conhecimento e recuperação. Reutilize os scripts
de ../feature-00c/scripts/; não crie um segundo modelo nem scheduler.
Para continuar ou abortar estado existente, use agente-00c-resume ou
agente-00c-abort e leia ../feature-00c/references/lifecycle.md.
Use --kind project em context.sh, session.sh, phase.sh e controller.sh.
--short-name é a identidade canônica kebab-case do projeto e deve coincidir
com --canonical-project no bootstrap. O estado fica em
.claude/agente-00c-state; os artefatos de desenvolvimento ficam em
docs/specs/<canonical-project>/. Não renomeie diretórios existentes sem
reconciliação explícita.
Um projeto novo não precisa de briefing nem constitution prévios. O bootstrap
começa em briefing. Antes da primeira onda, obtenha respostas reais do operador
para atomic_commit, roadmap_mode e delivery_tier e registre cada resposta
com scripts/optins.sh --project <raiz> --short-name <slug> --kind project --field <campo> --value <valor> --channel structured|prose --response-source <referência à resposta real> (ou cstk_optin com os mesmos campos no MCP).
Ausência de resposta não autoriza assumir
valores. Os helpers canônicos persistem essas escolhas; o gate I-2 exige as
três respostas. Para delivery_tier use local, internal-network, cloud-internal
ou cloud-public. Uma escolha explícita inicial permite ajustar o valor restritivo
inicial; alterações posteriores exigem reconciliação.
A pipeline padrão contém briefing, constitution, specify, clarify, plan, checklist, create-tasks, execute-task, converge, review-task e review-features. Com roadmap_mode explicitamente true, use briefing, constitution e roadmap. Leia a skill e a referência retornadas pelo descritor antes de executar cada fase. Roadmap não tem skill dedicada: leia a referência root e use roadmap-write.sh para persistir entradas e auditar seu resultado. Na constitution, o controlador aplica o pre-flight canônico e bloqueia conflitos até resposta humana autorizadora. Não responda em nome do operador.
Ao concluir briefing e constitution, o controlador registra hashes dos
artefatos de governança. Mudanças posteriores exigem reconciliação. Cada
conclusão exige arquivos reais, justificativa e os gates compartilhados.
O relatório de projeto é .claude/agente-00c-report.md.
O plugin registra o servidor cstk_pipeline. Selecione a raiz absoluta da
sessão com cstk_select_execution, kind=project e short_name igual à
identidade canônica; informe knowledge_db absoluto quando configurado.
As demais chamadas seguem a entrada feature-00c, com os três opt-ins reais.
O transporte stdio e o lock entre chamadas foram validados pelo app-server;
isso não certifica cobertura de hooks em um turno de modelo. Mantenha
autonomous_ready=false até a validação real dessas condições.
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.
- 10d ago First seen · 60 lines · 34 tokens per session scan A 4c893447cde7
agente-00c is a skill published in the GitHub repository JotJunior/cstk (24 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 800 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.