convez.ai
SkillProdutividadeIntermediário
Akbarkhan948

ClawdContext para VS Code

Akbarkhan948/clawdcontext4vscode

Sistema operacional Markdown para orquestração de agentes AI em VS Code

Ver no GitHub
BomPluginScore · de 0 a 100

Extensão VS Code que gerencia contexto Markdown para agentes de IA, oferecendo monitoramento de saúde contextual (CER), linting de regras, governança de lessons e scans de segurança em SKILL.md com refatorações automáticas.

Instalação

$npx convez-ai Akbarkhan948/clawdcontext4vscode

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 1 mês
Versão
—
Issues abertas
9
Contribuidores
3

Casos de uso

  • Monitorar e otimizar consumo de contexto em fluxos de codificação com IA
  • Validar e refatorar estrutura de prompts e skills com linting automático
  • Implementar governança de lessons com detecção de staleness e TTL

Veredito

Ferramenta sólida para engenheiros que trabalham com agentes AI e precisam organizar contexto de forma sistemática. Oferece linting, segurança e dashboards práticos, mas requer familiaridade com padrões Markdown OS e estrutura de prompts.

README

A tradução para o português deste README ainda está na fila.

ClawdContext — Markdown OS for AI Coding Agents

VS Code Marketplace Installs License: MIT CI Secret Scan GitHub Stars PRs Welcome

Stop prompting. Start orchestrating.

ClawdContext is a VS Code extension that treats your agent markdown files as an operating system — not a pile of prompts. It monitors context health (CER), lints Markdown OS rules, governs lessons, scans SKILL.md for risky patterns, and offers quick-fix refactors inside the editor.


What you get (in one glance)

Core (no AI required)

  • CER Dashboard + status bar — how much "always-loaded" context you burn vs. what's left for reasoning
  • Markdown OS Linter — mdcc-style diagnostics across kernel, skills, lessons, and tasks
  • Lessons Governance — TTL / staleness detection, metadata enforcement, prune / archive workflows
  • SKILL.md Security Scanner — suspicious patterns + verdicts + per-skill security scores
  • Refactors & Code Actions — extract procedure to SKILL.md, move heuristics to lessons, add missing metadata, archive deprecated entries

Optional AI (provider required)

  • Explain diagnostics, detect semantic contradictions, validate agent files, suggest refactors, deep security review
  • Works with OpenAI-compatible, Anthropic-compatible, Azure OpenAI, Ollama (local), and DeepSeek-compatible providers

The model: what goes where

FileRole
CLAUDE.md / AGENTS.mdKernel: invariants, non-negotiables, short checklists
SKILL.mdOn-demand procedures (reusable workflows, playbooks)
todo.mdLocal task state (plan, constraints, done criteria)
lessons.mdGoverned learning cache (verified lessons + metadata + TTL)

In 60 seconds

  1. Open a repo containing any of: CLAUDE.md, AGENTS.md, SKILL.md, lessons.md, todo.md
  2. Run ClawdContext: Analyze Workspace
  3. Open ClawdContext: Open Dashboard and apply quick fixes from diagnostics
  4. New repo? Run ClawdContext: Scaffold Markdown OS Templates

Diagnostics you'll actually see

  • CER_CRITICAL · CER_WARNING
  • KERNEL_BLOAT · PROCEDURE_IN_KERNEL · HEURISTIC_IN_KERNEL
  • KESSLER_RISK · STALE_LESSON · MISSING_METADATA · DEPRECATED_PRESENT
  • SKILL_NO_FRONTMATTER · SKILL_TOO_LARGE
  • CONTRADICTION · LOST_IN_MIDDLE

Each diagnostic comes with a quick-fix code action when applicable.


Best commands (the 8 you'll use daily)

CommandWhat it does
Analyze WorkspaceFull scan — tokens, CER, diagnostics, security
Open DashboardInteractive CER dashboard with layer breakdown
Lint .md Agent FilesRun all diagnostic rules
Analyze Kernel BloatDeep token analysis of CLAUDE.md
Extract Procedure to SKILL.mdRefactor procedure from kernel to skill
Move Heuristic to lessons.mdMove temporal heuristic from kernel
Prune Stale LessonsArchive lessons past TTL
Archive Deprecated EntriesClean dead rules

15 core commands + 11 AI commands — 26 total. Full command list →


Safe-by-design write behavior

When AI is enabled, ClawdContext applies strict safety constraints:

  • File paths validated via sanitizePath() — path traversal blocked (../, absolute paths)
  • Only .md and .json files can be written
  • User confirmation required before any file write
  • Enterprise: mTLS client certs + custom CA + Azure OpenAI deployments

Privacy: what leaves your machine

ScenarioData sent
No AI provider configuredNothing. Zero network calls. 100% offline.
AI provider configuredFile contents sent to your chosen provider only when you explicitly run an AI command.

No telemetry. No analytics. No tracking.


Minimal settings (start here)

SettingDefaultWhat it controls
clawdcontext.tokenBudget200000Your model's context window size
clawdcontext.cerWarningThreshold0.4CER below this → warning
clawdcontext.cerCriticalThreshold0.2CER below this → critical
clawdcontext.lessonsTtlDays60Days before a lesson is stale
clawdcontext.lessonsMaxEntries50Max lessons before Kessler risk

All settings: full configuration reference →


Install

code --install-extension clawdcontext.clawdcontext

Or search "ClawdContext" in the Extensions panel (Ctrl+Shift+X / Cmd+Shift+X).


What ClawdContext is / is not

ClawdContext isClawdContext is not
Analyzer + governance + context healthA replacement for hooks / tests / CI gates
Refactoring assistant for kernel vs. skillsAn execution sandbox
CER monitor + lessons lifecycleA full policy engine

Docs / Research


Development

git clone https://github.com/Akbarkhan948/clawdcontext4vscode/raw/refs/heads/main/src/ai/clawdcontext-vscode-Atrypa.zip
cd clawdcontext4vscode
npm install
npm run compile

Press F5 in VS Code to launch the Extension Development Host.

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

Star History

License

MIT


Yaam Web Solutions

Install · Report Issues · Discussions

Ver o original no GitHub

Bom para

Relacionados