Skip to content

t1k:context

FieldValue
Modulet1k-base
Version5.15.36
Effortmedium
Tools—

Keywords: agent-context, context-window, degradation, injection, optimize, tokens

/t1k:context
[topic or question]

Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage across all T1K workflows.

  • Designing/debugging T1K agent systems (cook, fix, debug, test, review)
  • Context limits constrain subagent performance
  • Optimizing cost/latency in multi-agent pipelines
  • Building module-scoped context injection
  • Implementing agent memory and cross-session persistence
  1. Context quality > quantity — High-signal tokens beat exhaustive content
  2. Attention is finite — U-shaped curve favors beginning/end positions
  3. Progressive disclosure — Load information just-in-time (sessionBaseline → keyword match → references)
  4. Isolation prevents degradation — Partition work across subagents
  5. Measure before optimizing — Know your baseline

IMPORTANT: Sacrifice grammar for concision. Pass these rules to subagents.

TopicReference
Measure (start here)token-audit.md (./references/token-audit.md)
Fundamentalscontext-fundamentals.md (./references/context-fundamentals.md)
Degradationcontext-degradation.md (./references/context-degradation.md)
Optimizationcontext-optimization.md (./references/context-optimization.md)
Compressioncontext-compression.md (./references/context-compression.md)
Memorymemory-systems.md (./references/memory-systems.md)
Multi-Agentmulti-agent-patterns.md (./references/multi-agent-patterns.md)
Evaluationevaluation.md (./references/evaluation.md)
Tool/Skill Designtool-design.md (./references/tool-design.md)
Pipelinesproject-development.md (./references/project-development.md)
Runtime Awarenessruntime-awareness.md (./references/runtime-awareness.md)
T1K Patternst1k-patterns.md (./references/t1k-patterns.md)

Measure First — Principle 5 Has a Runner

Section titled “Measure First — Principle 5 Has a Runner”
bun .claude/scripts/t1k-token-audit.cjs --days 7 --text

Emits facts from the session transcripts: Claude-quota vs routed-provider split, mean context carried per request, cache read:write ratio, boot cost, and mid-session cache busts. Establish this baseline before optimizing anything — and before trusting a routing percentage, which counts spawns, not tokens, and excludes the main session entirely. Reading the output: token-audit.md (./references/token-audit.md).

  • Token utilization: warning 70%, optimize 80%
  • Multi-agent cost: ~15x single agent baseline
  • Compaction target: 50–70% reduction, <5% quality loss
  • Cache hit target: 70%+ for stable workloads
  • Anthropic context/request: < 120K (above ~300K, read volume dominates the bill)
  1. Write — Save context externally (scratchpads, files, plans/)
  2. Select — Pull only relevant context (module scoping, skill activation)
  3. Compress — Reduce tokens while preserving info
  4. Isolate — Split across subagents (context partitioning)

T1K hooks auto-inject usage awareness via PostToolUse. Thresholds: 70% WARNING, 90% CRITICAL. See runtime-awareness.md (./references/runtime-awareness.md) for configuration details.

  • Exhaustive context over curated context
  • Critical info in middle positions
  • No compaction triggers before limits
  • Single agent for parallelizable tasks
  • Injecting all installed module skills into every subagent
  • Duplicating hook logic in AI responses
  • Never include secrets, tokens, or credentials in context passed to subagents
  • Scope injected context to the minimum needed for the task
  • Do not log or persist sensitive tool outputs in plans/ or memory files
  • Follow rules/security.md for all context-handling operations