메뉴
Audit context window consumption across skills, rules, MCP tools, CLAUDE.md, and memory. Surface bloat and recommend optimizations. Inspired by ECC context-budget.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when a pull request needs review by a different AI model than the one that authored it, or when configuring cross-model code review pipelines in CI/CD.
Run Demerzel's autonomous driver — full cycle or individual phases across all repos
Capture meaningful session state (current cursor, in-flight work, live hypotheses, open questions, do-NOT-carry-forward, success criteria) to state/digests/latest.md so the next session — including one after auto-compaction — can re-enter without re-discovering context cold. Distinct from /learnings (which captures surprises). Validates against docs/contracts/digest-schema.json.
Autonomous research scheduler — selects the most under-researched department by coverage ratio, generates questions from completeness gaps, cross-model validates, auto-produces courses at T>=0.8, rate-limited to 6 cycles/day with kill switch
Personalized AI tutor — turns any topic into a customized, progress-tracked learning course. Use when the user wants to LEARN a concept, skill, language, tool, or domain. Creates a MISSION, curated RESOURCES, iterative lessons with self-checks, and learning-records that persist across sessions. NOT for interrogating the user about their own design (use brainstorming/IDSD for that).
Run one bounded supervised autonomous cycle on the Demerzel governance repo. Picks the smallest unchecked governance slice inside allow_edit, implements it, runs the oracle (`pwsh scripts/verify.ps1`), emits cycle evidence, and stops. Refuses to run unless dev-process-overseer reports loop-eligible and the preflight passes. Use when asked to "run one supervised loop", "advance governance autonomously", or "do one cycle and stop".
| name | demerzel-context-budget |
| description | Audit context window consumption across skills, rules, MCP tools, CLAUDE.md, and memory. Surface bloat and recommend optimizations. Inspired by ECC context-budget. |
Analyze token consumption across every loaded component and surface actionable optimizations.
/demerzel context-budget — full audit
/demerzel context-budget --quick — summary only
With 36+ skills, 22 policies, .claude/rules/, CLAUDE.md, memory files, and 200+ MCP tool schemas loaded, sessions can burn 50K+ tokens before the user says anything. This skill measures the actual overhead and identifies savings.
Scan all component directories and estimate token consumption (words x 1.3):
Skills (.claude/skills/*/SKILL.md)
Rules (.claude/rules/*.md)
CLAUDE.md chain
Memory (~/.claude/projects/.../memory/MEMORY.md)
MCP Tool Schemas
Personas (personas/*.persona.yaml)
| Bucket | Criteria | Action |
|---|---|---|
| Always loaded | Rules, CLAUDE.md, MEMORY.md index, skill list | Optimize aggressively |
| On-demand | Skills (loaded when invoked), memory files | Optimize if large |
| Background | MCP schemas (loaded when tool used) | Monitor tool count |
| Never loaded | Personas, schemas, policies (not in context) | No action needed |
Context Budget Report
═══════════════════════════════════════
Total estimated overhead: ~XX,XXX tokens
Context model: Claude Opus 4.6 (1M window)
Effective available: ~XXX,XXX tokens (XX%)
Component Breakdown:
┌─────────────────┬────────┬───────────┐
│ Component │ Count │ Tokens │
├─────────────────┼────────┼───────────┤
│ Rules │ N │ ~X,XXX │
│ CLAUDE.md │ N │ ~X,XXX │
│ Memory index │ 1 │ ~X,XXX │
│ Skill list │ N │ ~X,XXX │
│ MCP schemas │ N │ ~XX,XXX │
└─────────────────┴────────┴───────────┘
Issues Found (N):
[ranked by token savings potential]
Top Optimizations:
1. [action] → save ~X,XXX tokens
2. [action] → save ~X,XXX tokens
3. [action] → save ~X,XXX tokens
Potential savings: ~XX,XXX tokens (XX%)
If --fix flag is passed:
Inspired by Everything Claude Code context-budget skill. Adapted for Demerzel's governance framework.