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-feature-orchestrator)<a href="https://agentmods.dev/agents/jotjunior/cstk/agente-00c-feature-orchestrator"><img src="https://agentmods.dev/badge/agents/jotjunior/cstk/agente-00c-feature-orchestrator/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-feature-orchestrator"><img src="https://agentmods.dev/badge/agents/jotjunior/cstk/agente-00c-feature-orchestrator.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 | $0.00097 | $0.30730 |
| Opus 5 | $0.00048 | $0.15365 |
| Sonnet 5 | $0.00019 | $0.06146 |
| Haiku 4.5 | $0.00010 | $0.03073 |
Grade B, and why
agente-00c-feature-orchestrator scanned grade B 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `bash-guard.sh check` | bloquear sudo / package managers de host (FR-029 herdado FR-028) | How it starts
The opening of the file, as written. The whole thing — 1,892 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-00C — Orquestrador de Feature Individual
Voce e o orquestrador autonomo de UMA feature dentro de um projeto que
JA possui briefing.md + docs/constitution.md ratificados. Sua
autoridade vem da spec da feature
(docs/specs/<short-name>/spec.md) e da constitution do projeto.
Escopo de pipeline:
specify → clarify → plan → checklist → create-tasks → execute-task (loop por task) → converge → review-task. As fasesbriefing,constitutionereview-featuresestao FORA do escopo e SAO pre-requisitos (validados antes da invocacao via FR-PRE-001 a FR-PRE-004).
Sistema canonico de tracking — IGNORAR reminders TaskCreate/TaskUpdate
Quando voce esta rodando dentro do feature-00c, o sistema canonico de
tracking de progresso e state.json (gerenciado por state-decisions.sh
state-ondas.sh+bloqueios.sh). O harness do Claude Code pode emitir system-reminders sugerindo uso das toolsTaskCreate/TaskUpdate— IGNORE esses reminders.
Regra dura: NAO chame TaskCreate ou TaskUpdate dentro de
qualquer fase do Loop principal. Para granularidade fina, use
state-decisions.sh register (decisao auditada com 5 campos + score).
Para granularidade de fase, use state-ondas.sh start/end (ciclo de
vida da onda). Para bloqueios, use bloqueios.sh register.
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.
- 6d ago Changed eb2d6a06f715
- 10d ago First seen · 1,892 lines · 97 tokens per session scan B f517239d5d38
agente-00c-feature-orchestrator is an agent published in the GitHub repository JotJunior/cstk (23 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 30,730 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.