AGENT SKILL

token-budget-governor

Prevent token waste across GPT, Codex, Claude, DeepSeek and local/free models by enforcing scoped prompts, compact context and narrow internal lenses contracts. Use when the user requests token budget governor or invokes token-budget-governor. Do NOT use to promote unverified claims or transient task status into durable memory.

License 许可
CC-BY-4.0
最近更新
2026-11-14
Stars
★ 1
Forks
0

01 前言 Front Matter

name
token-budget-governor
license
CC-BY-4.0
metadata
{ "author": "AEOS", "version": "1.0.0", "owner_agent": "codenavi-agent" }
description
Prevent token waste across GPT, Codex, Claude, DeepSeek and local/free models by enforcing scoped prompts, compact context and narrow internal lenses contracts. Use when the user requests token budget governor or invokes token-budget-governor. Do NOT use to promote unverified claims or transient task status into durable memory.

02 资源文件 2

03 SKILL.md 正文

Skill: token-budget-governor

Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md. Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF. Source roles/workers are internal lenses. Never create agent identities or bypass runtime secret/permission gates.

Mission

Prevent token waste across GPT, Codex, Claude, DeepSeek and local/free models by enforcing scoped prompts, compact context and narrow subagent contracts.

Allowed Actions

  • Estimate prompt and output token budgets.
  • Recommend context reduction.
  • Split budgets across subagents.
  • Block unbounded or unrequested work.
  • Generate token budget reports.

Forbidden Actions

  • Broadcast full context to all subagents.
  • Re-read whole repositories without evidence of need.
  • Expand scope without user approval.
  • Use long-context models when targeted reads are enough.
  • Continue after the requested task is satisfied.

Required Inputs

  • provider
  • prompt_scope
  • requested_output_tokens
  • task_priority
  • subagent_count

Output Schema

{
  "status": "PASS|REVIEW|BLOCKED",
  "estimated_tokens": 0,
  "limit": 0,
  "provider": "",
  "subagent_budget": 0,
  "recommendations": [],
  "blocking_conditions": []
}

Quality Gates

  • Prompt uses file refs instead of pasted files when possible.
  • Subagents receive only narrow task contracts.
  • Output schema is explicit.
  • Stop conditions are explicit.
  • Provider limits are respected.

Stop Conditions

  • Prompt exceeds provider budget.
  • Subagent scope is broad or duplicated.
  • Missing output schema.
  • Unrequested work detected.

Provenance and source freshness: provenance.

Example usage and failure handling: read usage and verification when selecting this skill or a required step fails.

04 同仓库更多 Skills

paulosantanna
paulosantanna/ai-assistent-universal-coder

workspace-brain

Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor/Codex/OpenCode/Claude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

workbench-profile-resolver

Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

wordpress-expert

Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation/modification, the complete installed plugin universe, governed remote wp-admin operations, themes/blocks/layout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

whatsapp-simulator

Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

web-quality-audit

Assimilated TLC/web-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

voiceai

Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio/video media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.

★ 1