// Audits agent context window usage via debug logs, token profiling, and redundancy detection. USE FOR: context optimization, token waste analysis, debug log parsing, hand-off gap analysis. DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture design, deployments.
| name | context-optimizer |
| description | Audits agent context window usage via debug logs, token profiling, and redundancy detection. USE FOR: context optimization, token waste analysis, debug log parsing, hand-off gap analysis. DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture design, deployments. |
| compatibility | Requires Python 3.10+ for log parser script |
Structured methodology for auditing how GitHub Copilot agents consume their context window. Identifies waste, recommends hand-off points, and produces prioritized optimization reports.
applyTo glob patterns| Capability | Description |
|---|---|
| Log Parsing | Extract structured data from Copilot Chat debug logs |
| Turn-Cost Profiling | Estimate token spend per turn from timing and model metadata |
| Redundancy Detection | Find duplicate file reads, overlapping instructions |
| Hand-Off Gap Analysis | Identify agents that should delegate to subagents |
| Instruction Audit | Flag overly broad globs and oversized instruction files |
| Report Generation | Structured markdown report with prioritized recommendations |
.github/agents/*.agent.md (or equivalent)Copilot Chat writes debug logs automatically to the VS Code log directory. To find the latest logs:
find ~/.vscode-server/data/logs/ -name "GitHub Copilot Chat.log" -newer /tmp/marker 2>/dev/null \
| sort | tail -5
For richer output, set github.copilot.advanced.debug.overrideLogLevels
in VS Code settings to capture verbose tool-call data.
📋 Reference: Read references/analysis-methodology.md for the complete methodology including:
ccreq line parsing, request types, latency heuristicsSee templates/optimization-report.md for the full output template.
This skill contains no project-specific logic. To use in another project:
.github/skills/context-optimizer/ to the target repo.github/agents/11-context-optimizer.agent.md.github/instructions/context-optimization.instructions.mdtools/scripts/snapshot-agent-context.sh and tools/scripts/diff-context-baseline.shtools/scripts/parse-chat-logs.py — Log parser producing structured JSONtemplates/optimization-report.md — Report output templatereferences/token-estimation.md — Detailed token cost heuristics| Reference | When to Load |
|---|---|
references/token-estimation.md | When estimating token counts for context optimization |
references/analysis-methodology.md | Log format, 5-step methodology, optimization patterns, baseline comparison |
Artifact template structures, H2 compliance rules, and documentation styling for agent outputs (Steps 1-7). USE FOR: generating any agent artifact, checking H2 structure compliance. DO NOT USE FOR: Azure resource configuration (use azure-defaults), Bicep/Terraform patterns (use bicep-patterns or terraform-patterns).
Deterministic Azure Policy discovery: lists effective policy assignments at subscription scope (including MG-inherited), pulls definitions and exemptions, classifies effects, filters Defender auto-assignments, and emits the governance-constraints JSON envelope via a Python script. USE FOR: 04g-Governance Phase 1 discovery, refreshing `04-governance-constraints.json`. DO NOT USE FOR: artifact writing, architecture mapping, traffic-light rendering, challenger orchestration — those stay in the parent agent.
Authoritative reference for VS Code Copilot customization mechanisms: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when deciding which customization type to use, creating new .instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json files from scratch, or debugging why a customization is not loading. DO NOT USE FOR: routine file edits where the format is already known.
Azure infrastructure defaults: regions, tags, naming (CAF), AVM-first policy, security baseline, unique suffix patterns. USE FOR: any agent generating or planning Azure resources. DO NOT USE FOR: artifact template structures (use azure-artifacts), pricing lookups (read references/pricing-guidance.md on demand).
Runtime context compression for agents approaching model context limits. Defines 3 compression tiers (full/summarized/minimal) with per-artifact templates. USE FOR: reducing artifact loading size at runtime, context budget management. DO NOT USE FOR: diagnostic context auditing (use context-optimizer), Azure infrastructure.
Shared IaC deploy patterns for Bicep and Terraform deploy agents: deployment strategies, circuit breaker, known deploy issues. For preflight validation (auth, governance, stop rules), see azure-validate. USE FOR: Phased deployment, circuit breaker, deploy-specific known issues. DO NOT USE FOR: Preflight validation (use azure-validate), code generation (use azure-bicep-patterns or terraform-patterns).