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 feature-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/feature-00c)<a href="https://agentmods.dev/skills/jotjunior/cstk/feature-00c"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/feature-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/feature-00c"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/feature-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 | $0.00033 | $0.01835 |
| Opus 5.5 | $0.00013 | $0.00734 |
| Sonnet 5.5 | $0.00007 | $0.00367 |
| Haiku 4.5 | $0.00003 | $0.00184 |
Grade A, and why
feature-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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-00C no Codex
Leia o contexto usando sh scripts/context.sh --project <raiz> --short-name <nome>, relativo a esta skill. Os scripts resolvem o runtime
versionado pelo próprio caminho, no checkout ou no pacote. O contexto não
certifica confiança dos hooks. autonomous_ready=false permite condução
supervisionada; não declara execução autônoma validada.
Preparação
Crie a execução autorizada com scripts/session.sh bootstrap --project <raiz> --short-name <nome> --description <descrição> --canonical-project <identidade>.
Briefing e constitution devem existir; constitution exige **Version**: X.Y.Z.
--observed-model só recebe um ID observado; omitido grava null.
Não reinicialize estado existente. Use a entrada feature-00c-resume para
continuar uma execução e feature-00c-abort para encerrá-la. Leia
references/lifecycle.md para os contratos de resposta, recuperação, handoff
e reconciliação. session.sh resume permanece uma validação sem abrir onda.
Antes da primeira onda, pergunte ao operador se deseja commits automáticos
por etapa. Não transforme autorização geral para desenvolver em opt-in de
commit. Registre a resposta recebida com scripts/optins.sh --project <raiz> --short-name <nome> --atomic-commit true|false --channel structured|prose --response-source <referência à resposta real>. A guarda I-2 permanece ativa.
O valor false também é uma resposta explícita. Respostas resolvidas não são
sobrescritas; não invente timeout, ausência nem canal observado.
Uma onda supervisionada
Quando o plugin e seu MCP estiverem conectados, prefira o transporte nativo:
chame cstk_select_execution no servidor cstk_pipeline com project igual
à raiz absoluta da sessão, kind=feature e short_name da feature autorizada.
O servidor começa sem projeto selecionado e vincula o primeiro projeto até
reiniciar; não deduza o alvo a partir do diretório instalado do plugin.
Se usar banco compartilhado configurado, informe knowledge_db absoluto
nessa seleção. O host não necessariamente repassa CSTK_KNOWLEDGE_DB ao MCP;
confirme o caminho retornado por cstk_context antes de abrir a onda.
What ships with it
15 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.
- references/lifecycle.md 6.7 KB
- scripts/_entry.sh 7.9 KB runs code
- scripts/_native.sh 2.8 KB runs code
- scripts/_session.sh 45 KB runs code
- scripts/_tools.sh 2.2 KB runs code
- scripts/context.sh 71 B runs code
- scripts/controller.sh 271 B runs code
- scripts/lifecycle.sh 329 B runs code
- scripts/mcp-bridge.sh 2.9 KB runs code
- scripts/native-mcp.sh 1008 B runs code
- scripts/native-status.sh 2.4 KB runs code
- scripts/optins.sh 69 B runs code
- scripts/phase.sh 69 B runs code
- scripts/session.sh 243 B runs code
- scripts/tools.json 5.2 KB
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 · 129 lines · 33 tokens per session scan A 5a5eb023353d
feature-00c is a skill published in the GitHub repository JotJunior/cstk (24 stars, last pushed 6d ago), licensed MIT. It adds 33 tokens to every session and 1,835 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.