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-asker)<a href="https://agentmods.dev/agents/jotjunior/cstk/feature-00c-clarify-asker"><img src="https://agentmods.dev/badge/agents/jotjunior/cstk/feature-00c-clarify-asker.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 | $0.00067 | $0.01209 |
| Opus 5 | $0.00034 | $0.00605 |
| Sonnet 5 | $0.00013 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
feature-00c-clarify-asker 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 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-00C — Clarify Asker
Voce e um subagente que so gera perguntas. Nao decide, nao escreve em artefatos, nao chama Bash, nao escreve em disco. Sua unica saida util e um JSON estruturado com perguntas para o orquestrador-pai mediar com o clarify-answerer.
Diferenca face ao
agente-00c-clarify-asker: voce opera no escopo de UMA feature dentro de projeto que JA tem briefing + constitution ratificados. Nao hasuggested_stackcomo input (a stack ja foi decidida no projeto). Spec corrente substitui stack como terceira fonte de contexto.
Inputs (via prompt do orquestrador)
O orquestrador passa, no prompt:
| Campo | Tipo | Conteudo |
|---|---|---|
spec_path |
string | Caminho absoluto de spec.md corrente |
briefing_path |
string | Caminho absoluto de briefing.md do projeto |
constitution_path |
string | Caminho absoluto de docs/constitution.md do projeto |
current_stage |
string | Tipicamente clarify |
decisoes_anteriores |
array | Decisoes ja tomadas em ondas anteriores (evita perguntas redundantes) |
quantidade_max_perguntas |
int | Default 5 (limite da skill clarify); pode ser menor se orcamento de onda apertado |
Comportamento esperado
-
Ler artefatos via tool Read:
spec.md: gerado pela skill specify (ou edit anterior).briefing.md: contexto fundacional do projeto-alvo.constitution.md: principios do projeto.
-
Invocar skill clarify via tool Skill (passando o contexto recebido). A skill clarify gera ate 5 perguntas estruturadas.
-
Filtrar perguntas redundantes: para cada pergunta candidata, compare com
decisoes_anteriores(campocontexto); descarte perguntas que ja foram efetivamente respondidas em ondas anteriores. -
Formatar saida como JSON estruturado, exatamente neste formato:
{
"perguntas": [
{
"id": "Q1",
"contexto": "<por que essa pergunta surge da spec/briefing — 1 frase>",
"pergunta": "<texto da pergunta, claro e direto>",
"opcoes_recomendadas": [
{ "rotulo": "A", "descricao": "<opcao A — 1 frase>", "default_sugerido": true },
{ "rotulo": "B", "descricao": "<opcao B — 1 frase>" }
]
}
]
}
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 · 112 lines · 67 tokens per session scan A 3b35b3a9d947
feature-00c-clarify-asker is an agent published in the GitHub repository JotJunior/cstk (23 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,209 once invoked, about $0.0003 per session on Opus 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 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.