---
id: "concept-icm-d2"
type: "concept"
source_timestamps: ["§1", "§3"]
tags: ["architecture", "agent-design", "file-systems"]
related: ["concept-five-layer-hierarchy", "concept-stage-contracts", "framework-icm-architecture", "claim-token-efficiency", "contrarian-frameworks-overkill"]
definition: "A method that replaces code-based agent orchestration with filesystem structure: numbered folders as stages, markdown files as context, scripts for mechanical work, one agent throughout."
sources: ["paper"]
sourceVaultSlug: "icm-paper-folder-architecture-2026Jun02"
originDay: 2
---
# Interpretable Context Methodology (ICM)

## Definition

ICM is the paper's central contribution: for sequential, human-reviewed, repeatable workflows, the **folder structure replaces the orchestration framework**. A single AI agent reads different context at each stage rather than multiple agents coordinating through code.

## How it works

- **Numbered folders** (e.g. `01_research`, `02_script`, `03_production`) represent pipeline stages.
- **Plain markdown files** carry the prompts and context that tell the agent what role to play at each step.
- **Local scripts** handle mechanical work that needs no AI.
- **Human review gates** sit at each output boundary — see [[concept-stage-contracts]].

The result is full pipeline capability with no framework code, no server, and no developer needed for day-to-day operation. The on-disk shape is documented in [[framework-icm-architecture]] and the context model in [[concept-five-layer-hierarchy]].

## Scope of the claim

ICM is positioned **not against frameworks in general** but against their use for a specific class of problem where they are overhead — see [[contrarian-frameworks-overkill]]. It explicitly does not address real-time multi-agent collaboration or high-concurrency systems; for those, tools like [[entity-autogen]] remain appropriate.

## Performance argument

The efficiency story (see [[claim-token-efficiency]]) is that scoped stages land at ~2–8k focused tokens versus a ~42k monolithic prompt that is mostly irrelevant. The mechanism is explained in [[concept-context-scoping]].

## Reference implementation

All workspaces were built and run with [[entity-claude-code]]. The methodology is formally articulated in [[entity-icm-paper]] by [[entity-jake-van-clief]] and [[entity-david-mcdermott]].


## Related across days
- [[concept-icm-d1]]
- [[concept-dialogue-structure]]
- [[concept-three-levels-ai]]
- [[framework-skill-creation]]
- [[arc-talk-vs-paper-altitude]]