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 review-featuresgit 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/review-features)<a href="https://agentmods.dev/skills/jotjunior/cstk/review-features"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/review-features/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/review-features"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/review-features.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.04598 |
| Opus 5.5 | $0.00022 | $0.01839 |
| Sonnet 5.5 | $0.00011 | $0.00920 |
| Haiku 4.5 | $0.00006 | $0.00460 |
Grade A, and why
review-features 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 2mo 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Revisar Portfolio de Features
Gere um relatorio comparativo de TODAS as features do projeto, com tabela agregada de progresso, criticidade pendente e sugestao de acao (arquivar, abandonar, priorizar ou continuar).
Pre-requisitos
Obrigatorio: pelo menos um diretorio agregador de features. Procurar nesta ordem:
docs/specs/*/— padrao SDD (cada feature em sua pasta comspec.md+tasks.md)docs/features/*/- Diretorio passado explicitamente pelo usuario
Cada subdiretorio deve conter pelo menos um tasks.md para entrar no
relatorio. spec.md e opcional (usado para extrair descricao).
Diferenca para review-task
| Aspecto | review-task | review-features |
|---|---|---|
| Escopo | UMA feature ou projeto | TODAS as features (cross-feature) |
| Saida | Status detalhado + top-3 tasks | Tabela comparativa + sugestao por feature |
| Atualiza arquivos? | Sim (marca tasks [x] baseado em evidencia) |
Nao (read-only) |
| Pergunta tipica | "qual a proxima task?" | "qual feature priorizar?" |
Se o usuario pediu progresso de UMA feature, use review-task. Se pediu
visao global ou comparacao entre features, use esta.
Proximos passos sugeridos
/review-taskem features marcadas comoPRIORIZARpara detalhar tasks/execute-taskna proxima task critica- Antes de mover uma feature
ARQUIVARparadocs/specs/_archived/<YYYY-MM-DD>-<feature>/, rodar o gate deterministicoscripts/delta-gate.sh docs/specs/<feature>/spec.md --corpus-dir docs/specs/current:- Exit != 0 (bloqueado): NAO mover a feature. Reportar ao operador os
FINDING|error|<code>|<mensagem>literais emitidos pelo gate e pedir que a secao## Delta Requirementsseja preenchida na spec, ou que um skip explicito seja registrado (vercontracts/delta-section-format.md). - Exit 0 (liberado): rodar
scripts/delta-merge.sh docs/specs/<feature>/spec.md --feature <feature>ANTES domvpara_archived/. Se o merge tambem bloquear (exit 1 — o corpus mudou entre o gate e o merge), omvfica igualmente suspenso (defesa em profundidade — o gate por si so nunca garante que o merge vai passar). - So apos o merge ter sucesso (exit 0) o
mvacontece — o fluxo de mover para_archived/permanece EXATAMENTE como hoje (acao manual, pedir confirmacao ao usuario antes de mover;<YYYY-MM-DD>e a data em que a acao de arquivamento de fato ocorre, nao a data de criacao da feature — permite ordenacao cronologica do diretorio sem abrir cada subpasta). Diretorios ja existentes sobdocs/specs/_archived/sem esse prefixo de data (arquivados antes desta convencao) permanecem inalterados — NAO renomear nem mover conteudo ja arquivado. O corpus canonico (docs/specs/current/) e ADICIONAL ao archive existente, nunca uma substituicao (FR-006).
- Exit != 0 (bloqueado): NAO mover a feature. Reportar ao operador os
What ships with it
7 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.
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.
- 2mo ago First seen · 390 lines · 56 tokens per session scan A 27f1eb4f1f17
review-features is a skill published in the GitHub repository JotJunior/cstk (24 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 4,598 once invoked, about $0.0002 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 2026-08-30.
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.
first-task
Guide the user's first Paperclip task when its description invokes /first-task. Interpret the opening answer, clarify their goal, propose a plan or a single task, and wait for approval before hiring agents or executing approved work.
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.