Context Budget Audit
Audit context window consumption across agents, skills, MCP servers, and rules. Identifies token bloat, redundant components, and produces prioritized savings recommendations. Target: under 10 MCPs, under 80 tools active.
Governance Receipt
- Signer
- sovereign-claw-ed25519
- Signed At
- 6/4/2026
- Risk Tier
- T2
- Receipt Hash
- 50685369
- Manifest Hash
- 5e1a6ca3e9e9b3201d8aaafcdb81ff1111e3e10739b5290f9303b5d72a236c1a
- Signature
- TfwCbyVG
- Root Public Key
- 349b0348
Skill Details
- Gate Verdict
- Elevated · Review
- Publication State
- published
- Risk Tier
- T2
- Manifest Hash
- 5e1a6ca3
Download Attested Bundle
Install Context Budget Audit
Each bundle is served from the attested copy of Context Budget Audit, so the file you download is the one covered by the governance receipt on this page rather than whatever currently sits at the upstream source.
Claude Code skill
curl -L "https://atestiv.com/api/download/ecc-context-budget-audit?format=claude-code" -o ecc-context-budget-audit.skill.mdMCP tool definitions
curl -L "https://atestiv.com/api/download/ecc-context-budget-audit?format=mcp" -o ecc-context-budget-audit.mcp-tools.jsonRaw attested bundle
curl -L "https://atestiv.com/api/download/ecc-context-budget-audit?format=raw" -o ecc-context-budget-audit.bundle.jsonVerify the bundle against its manifest hash
shasum -a 256 ecc-context-budget-audit.bundle.jsonProvenance
- Catalog identifier:
ecc-context-budget-audit - Harvested from the upstream repository.
- The manifest hash below is what the signing key committed to. A bundle whose digest does not match it is not the attested Context Budget Audit.
- Anything published here has been through the same gate, so a missing receipt is itself a signal rather than an omission.
More Skills
Inventory & Demand Planning
Supply chain demand planning patterns: demand forecasting, safety stock calculation, reorder point optimization, ABC/XYZ classification, seasonal adjustment, and inventory health scoring.
Context Compaction
Strategic context window compaction: compact after research before implementation, after milestones before next phase, after debugging before feature work, after failed approaches before new ones. Never mid-implementation.
Continuous Learning v1
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use. Legacy version superseded by v2 instinct system.