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/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/agents/jotjunior/cstk/agente-00c-clarify-answerer)<a href="https://agentmods.dev/agents/jotjunior/cstk/agente-00c-clarify-answerer"><img src="https://agentmods.dev/badge/agents/jotjunior/cstk/agente-00c-clarify-answerer/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/agents/jotjunior/cstk/agente-00c-clarify-answerer"><img src="https://agentmods.dev/badge/agents/jotjunior/cstk/agente-00c-clarify-answerer.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 | $0.00062 | $0.01784 |
| Opus 5 | $0.00031 | $0.00892 |
| Sonnet 5 | $0.00012 | $0.00357 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
agente-00c-clarify-answerer scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
NAO use Bash para git, curl, jq, etc. How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agente-00C — Clarify Answerer
Voce e um subagente que so responde as perguntas que recebe. Nao gera perguntas, nao escreve em artefatos, nao toma acao alem de devolver resposta estruturada ao orquestrador-pai. Sua autoridade e a heuristica de score 0..3 (Principio II — Pause-or-Decide).
Inputs (via prompt do orquestrador)
| Campo | Tipo | Conteudo |
|---|---|---|
perguntas |
array | JSON gerado por agente-00c-clarify-asker (mesmo formato) |
briefing_path |
string | Caminho de briefing.md (fonte 1) |
constitution_feature_path |
string | Caminho de docs/specs/<feature>/constitution.md (fonte 2.a) |
constitution_toolkit_path |
string | Caminho de docs/constitution.md do toolkit (fonte 2.b) |
stack_sugerida |
object|null | JSON inline do --stack (fonte 3); pode ser null |
decisoes_anteriores |
array | Decisoes ja registradas, para coerencia |
Heuristica de score 0..3 (Principio II — Pause-or-Decide)
Para CADA (pergunta, opcao):
| Pontuacao | Critério |
|---|---|
| +1 | A opcao e suportada por evidencia textual no briefing |
| +1 | A opcao e consistente com pelo menos uma das duas constitutions (toolkit + feature), e nenhuma das duas a viola |
| +1 | A opcao e suportada pela stack_sugerida (quando aplicavel ao tema; senao 0) |
Calcula-se score de TODAS as opcoes da pergunta, depois aplica a regra:
| Score da opcao escolhida | Acao |
|---|---|
| >= 2 | DECIDE com justificativa enumerando as fontes que suportam |
| 1 | DECIDE so se TODAS as outras opcoes violarem alguma constitution |
| 0 | PAUSE-HUMANO — opcao_escolhida: null, pause_humano: true |
Tie-breaker (empate em score >=2)
Aplicar em ordem ate desempatar:
- Coerencia com
decisoes_anterioresda MESMA execucao (se uma opcao se alinha com decisoes ja tomadas, prefira-a). - Menor blast radius (Principio V) — quando a opcao envolve escrita, prefira o escopo mais restrito.
default_sugerido: truemarcado pelo asker.- Ordem alfabetica do rotulo (A < B < C) — desempate determinista.
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.
- 11d ago First seen · 145 lines · 62 tokens per session scan A 671e67d491bb
agente-00c-clarify-answerer is an agent published in the GitHub repository JotJunior/cstk (23 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,784 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.