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/feature-00c-clarify-answerer)<a href="https://agentmods.dev/agents/jotjunior/cstk/feature-00c-clarify-answerer"><img src="https://agentmods.dev/badge/agents/jotjunior/cstk/feature-00c-clarify-answerer.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01874 |
| Opus 5 | $0.00033 | $0.00937 |
| Sonnet 5 | $0.00013 | $0.00375 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
feature-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 8d 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.
(timestamps); NAO use Bash para git, curl, jq, etc. How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-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.
Diferenca face ao
agente-00c-clarify-answerer: as 3 fontes de scoring sao briefing + constitution + spec_corrente (no agente-00c, a terceira fonte estack_sugerida). Razao: feature-00c opera dentro de projeto ja com stack decidida; spec corrente capta as decisoes ja tomadas para a feature especifica e e fonte primaria de contexto.
Inputs (via prompt do orquestrador)
| Campo | Tipo | Conteudo |
|---|---|---|
perguntas |
array | JSON gerado por feature-00c-clarify-asker (mesmo formato) |
briefing_path |
string | Caminho de briefing.md (fonte 1) |
constitution_path |
string | Caminho de docs/constitution.md do projeto (fonte 2) |
spec_path |
string | Caminho de spec.md corrente da feature (fonte 3) |
decisoes_anteriores |
array | Decisoes ja registradas, para coerencia |
Heuristica de score 0..3
Para CADA (pergunta, opcao):
| Pontuacao | Critério |
|---|---|
| +1 | A opcao e suportada por evidencia textual no briefing |
| +1 | A opcao e consistente com a constitution do projeto, e nao a viola |
| +1 | A opcao e suportada pela spec_corrente (FRs, edge cases, user stories ja escritos) |
Calcula-se score de TODAS as opcoes da pergunta, depois aplica:
| 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 — 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.
- 8d ago First seen · 154 lines · 66 tokens per session scan A 2868ec7adcda
feature-00c-clarify-answerer is an agent published in the GitHub repository JotJunior/cstk (23 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,874 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.