Harness Handbook
Free while signed in. Answers cite the passages they came from.
Harness Handbook treats behavior localization as the missing layer in agent-harness evolution. It automatically builds a three-level behavior-to-source map with static analysis and LLM-assisted structuring, then uses Behavior-Guided Progressive Disclosure to guide coding agents from system behaviors to verified edit locations. Across 60 modification requests on Codex and Terminus-2, handbook assistance raised planning win rates from 28.3% to 38.3% and from 26.7% to 45.6%, while cutting planner tokens by 12.7% and 8.6%. File- and symbol-level F1 improved in all 24 comparisons against GPT-5.5 and Opus 4.8 reference plans.
Synthesized automatically: The Handbook is built from the harness codebase through static analysis and LLM-assisted structuring, so the representation is generated rather than hand-maintained and can be regenerated as the harness changes.
A three-level map: It progresses from an L1 system overview of architecture, execution model, and data flow, to L2 component overviews with responsibilities, inputs, outputs, and state, down to L3 source-backed unit details, with a navigation pane for cross-stage tracing.
Behavior-Guided Progressive Disclosure: BGPD walks an agent from a high-level behavior to the relevant implementation, then verifies candidate locations against the current source, so edits land on the right files instead of plausible-looking wrong ones.
Why it matters: As self-improving harnesses grow, the bottleneck shifts from writing changes to locating them, and a readable, navigable, editable representation gives builders and agents a shared map for safely evolving production systems.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack