Researcher & builder

StatusShipped

Context Compression

Value engineering, not size reduction

I designed a structured format for agent-facing context: nine sections, explicit token budgets, and a six-pass compression pipeline from stripping known explanations down to safe truncation order, each pass logged for reproducibility. I exercised it through an MCP server, a CLI prototype, and dozens of hand-converted documents.

decisions, interfaces, and constraints are never trimmed to hit a token budget
Verbatim from the project record -- connective words fade, load-bearing terms hold.

Project brief

Shipped

Problem

Shorter context is not useful if compression removes the decisions, interfaces, and constraints an agent needs.

Outcome

Converts long-form documentation into a compact, structured format that preserves decisions, interfaces, and constraints for language-model agents. Optimizes for value delivered per token, rather than raw size reduction.

Evidence

  • Dual channels and rule layers (July 2025) is the earlier architecture note behind offline distill → attach.
  • A protocol-based validation service checks structure and fact presence locally without a model call; a small command-line prototype handles conversion, merging, and section extraction.
  • Five additional capabilities and an automated orchestration layer are specified but not implemented; none are presented as shipped.

Key decisions

  • Specification: A structural format with required sections, token budgets, and an ordered compression pipeline that never trims decisions, interfaces, or constraints.
  • Tooling: A protocol-based validation service checks structure and fact presence locally without a model call; a small command-line prototype handles conversion, merging, and section extraction.
  • Applied & research: The format was applied by hand across dozens of internal documents and checked against a survey of twenty external papers on compression and context management.
  • Forward roadmap: Five additional capabilities and an automated orchestration layer are specified but not implemented; none are presented as shipped.

The rule

Teams that adopted it anecdotally reported fewer clarification rounds; that is an impression, not a benchmark.

System map

The figures show the methodology's ecosystem of spec, tooling, and research radiating from one core approach.

Ecosystem map
Context-compression methodologyvalue-per-token, not raw size reduction
Specificationstructural format, token budgets, ordered compression pipeline
Toolinga validation service, a prototype CLI, agent prompts
Applied & researchdozens of converted documents, a 20-paper survey
Forward roadmapfive additional capabilities, an automation layerspecified only, not yet built
A single compression methodology anchors a formal spec, a tooling layer, an applied research corpus, and a forward roadmap that has not been built yet.

Four-part structure

Five additional capabilities and an automated orchestration layer are specified but not implemented.

Identity
Facts
Relationships
Next actions

Six ordered passes

Compress for agents, not humans is the methodology write-up.

The step-by-step loop a document moves through from profiling to validation, with failures routed back rather than shipped.

The five stages below are the validation loop a document travels end to end; the six passes described above run inside stage 03, Compress & render.

Transformation & validation loop
1Profile contentsize, type, repetition
2Extract structuredecisions, interfaces, constraints, relationships
3Compress & renderordered layers, required sections
4Validategaterequired sections + fact presence
5Ship or loop backfailure returns to structure extraction, not partial output
A document is profiled, its load-bearing facts extracted, compressed, and rendered; a failed validation check sends it back for another pass rather than shipping a lossy result.

Applied & research

Dual channels and rule layers is the earlier architecture note.

The format was applied by hand across dozens of internal documents and checked against a survey of twenty external papers on compression and context management.

A protocol-based validation service checks structure and fact presence locally without a model call; a small command-line prototype handles conversion, merging, and section extraction.

Specified, not built

Five additional capabilities and an automated orchestration layer are specified but not implemented; none are presented as shipped.

Ecosystem map label: “specified only, not yet built”

An impression, not a benchmark

The same context-shaping habit shows up next to Modular Orchestration System and Connect Layer Plugin.

Skills

Portfolio graph

Hover nodes · click empty canvas to zoom/pan

Maps how the work here connects. Open the Portfolio graph →

  • Professional
  • Personal
  • Skill
  • Writing