process · reread-before-edit

Re-read before editing

Force the agent to read the current version of a file immediately before changing it.

The harness rejects an edit unless the file was read after its last modification, and edits are expressed as exact-match replacements that fail if the text has changed. Stale state then causes a visible failure instead of a silent bad edit.

Addresses: Tracking state through a long task

Contexts: Coding agent

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

Searched, still open

Looked for a controlled study isolating the harness rule itself: rejecting an edit unless the file was read after its last modification, with exact-match replacement so a changed file fails loudly. Found nothing that separates this from the surrounding agent scaffold. The adjacent literature is about context efficiency and repository exploration, which is a different intervention — it changes what the agent reads, not whether a stale read can be acted on. The measurable question is narrow and cheap to run: rate of silently wrong edits with and without the read-recency precondition, on the same task set.

Nearest miss
FastContext: Training Efficient Repository Explorer for Coding Agents

Deploys a separate exploration subagent to cut token spend and keep the solver's context clean, and reports end-to-end resolution gains. It never isolates stale-read edits, and its intervention is about what gets read rather than about refusing to act on an outdated read. Citing it here would look like support without being any.

searched 2026-09-04 · see open questions

Code

No repository linked yet. Contribute one.