| name | context-budget |
| description | Audit token overhead across .claude/agents/, .claude/skills/, .mcp.json, .claude/rules/, CLAUDE.md, MEMORY.md, CONTEXT.md. Identify bloat, redundancy, optimization targets. Run after adding components or when context feels heavy. |
| version | 1.0 |
| updated | "2026-04-29T00:00:00.000Z" |
| tags | ["meta","infrastructure","active"] |
| effort | medium |
| sources | ["https://github.com/affaan-m/everything-claude-code/blob/main/skills/context-budget/SKILL.md (MIT, Affaan Mustafa 2026)"] |
| related_skills | ["doc-audit","tech-debt-audit","skill-audit"] |
/context-budget — Token-overhead audit
Surface the token cost of every loaded component and rank what to trim. Token burn surfaces every few sessions (S141 Gemini autodream switch, S156 briefing-bloat audit, S180 Discord-bot edition currency). This skill makes the audit routine, not crisis-driven.
Distinct from /doc-audit (content staleness) and /tech-debt-audit (engine code health). This is purely about token economics.
When to use
- Session feels sluggish or output quality is degrading
- Just added agents, skills, or MCP servers
- Want to know how much context headroom is left
- Planning to add components and need to know if there's room
- Periodic maintenance — every 5–10 sessions
When NOT to use
- Routine work in progress — wait for a maintenance window
- Recent additions are still being evaluated — don't audit before they prove out
- Mid-cycle (between sift and post-publish) — wait until cycle closes
What to scan
Agents (.claude/agents/<name>/)
Each canon-fidelity agent carries four files: IDENTITY.md + LENS.md + RULES.md + SKILL.md. Token cost per agent = sum across all four. Description-field cost is special — loaded into every Task tool spawn even if the agent is never invoked.
Surface: 25 canon-fidelity agents × 4 = 100 files. Plus engine-validator (code-only, scope-noted N/A).
Flag patterns:
- Agent description > 30 words (Pocock/affaan-m bloat threshold)
- IDENTITY.md > 80 lines
- RULES.md > 200 lines (canon-fidelity rules bulk fast if not pruned)
- LENS.md duplicates IDENTITY.md content
- Agents not invoked in 20+ sessions (deprecate candidates)
Skills (.claude/skills/<name>/SKILL.md)
Single SKILL.md per skill (some have supporting files). Description loads with skill registration. Body loads only when invoked.
Surface: ~80+ skills currently.
Flag patterns:
- SKILL.md > 400 lines
- Description > 30 words
- Two skills with overlapping triggers (one will fire when the other should)
- Skills not invoked in 20+ sessions
MCP servers (.mcp.json + plugin MCPs)
Each tool schema costs ~500 tokens. Always loaded into context regardless of whether tool fires.
Surface: godworld (10 tools) + claude-mem + claude-in-chrome + + + + + + + + + + + .
