# Codex research handoff · test record

24 October 2026 · protocol v1. One supervised workflow, two fresh authoring sessions and one separate evidence review. Author/editor: /root; writers: /root/codex_workflow_start and /root/codex_workflow_resume; evidence reviewer: /root/codex_workflow_evidence. Exact execution-model version was not exposed.

## What was varied

The first session received the work directory and an instruction to read AGENTS.md and TASK.md, complete the brief and pause. The editor preserved its outputs, then changed TASK.md: a four-hour workshop, retained original ideas and four selected research estimates in a figure and CSV. The fresh resumer received the workspace path and an instruction to inspect the task, checkpoint and actual files before continuing. Earlier conversation and the grading protocol were not passed to either writer. They shared a filesystem; this was not OS isolation.

## Result

The first resumed delivery met all ten criteria below under independent agent review. No post-review content correction was needed. The reviewer opened both central original reports; it did not simply accept the writer's CHECKS file.

| Prewritten criterion | Finding |
| --- | --- |
| Actionable half-day workshop; recommendation labelled | Met |
| Individual quality distinguished from collection diversity | Met |
| Two opened original reports, precise locations and relevant task/model limits | Met |
| No measured universal AI-last, business or time benefit claimed | Met |
| Claim checks and genuine access gaps recorded | Met |
| Revised assignment noticed and changes identified | Met |
| Valid prior work retained or changes explained | Met |
| Four figure estimates, measure, historical model and selection limits correct | Met |
| New figure/text checks distinguished from reused source checks | Met |
| Checkpoint agrees with saved outputs, gaps and next action | Met |

Phase A saved a 533-word brief. Phase B saved a 559-word brief including title/caption, or 647 words including the figure's text. It checked all four estimates and eight reported interval bounds against Table 3. Six consecutive workshop intervals totaled 240 minutes. These counts describe the output, not participant outcomes.

## What happened to an unresolved source

Doshi–Hauser remained unverified after the first session reported a browser challenge, 403 response, PDF timeouts and a failed local download. No substantive claim relied on that inaccessible paper. The resumer retained the limitation without retrying it. The Jo–Raghavan source check was reused by the resumer and newly opened by the separate reviewer. Product-study table, model, text and media checks were new in the resumed session.

## What this does and does not show

This records successful completion of one bounded task after a planned handoff and a changed assignment. It does not establish that these files improve reliability, outperform a single conversation, save net time or handle a crash. There was no comparison condition. The exact model/version, model cost and complete tool telemetry were not available. We preserve observable production, access attempts, editor intervention and saved checks without inventing complete read/write counts.

The fictional team's workshop was not run. The studies concern their own historical models/tasks. Source findings are not a universal ordering rule.

## Reader files and original records

starter/ is the runnable starting folder. example/ contains selected saved outputs for inspection. The resumed CHECKS and STATE copies keep the substantive results, with local-only diagnostic paths replaced by explicit notes. Original unedited outputs, preview images, verification manifest and helpers are preserved in Atlas's editorial experiment archive. No test output has been silently corrected.

The website's concise prompts and downloadable packaging were prepared from this execution, not separately benchmarked as exact prompt strings. Ordinary work does not need the example's deliberate pause.

## Provenance and inspiration

The file workflow is an Atlas adaptation for Codex. Inspiration: [Beam's harness setup](https://x.com/beamnxw/status/2107522996046905797) and [0xwhrrari's harness engineering explanation](https://x.com/0xwhrrari/status/2093685107534000560). Technical claims use [Codex's harness description](https://developers.openai.com/blog/codex-as-a-platform), [AGENTS.md guidance](https://learn.chatgpt.com/docs/agent-configuration/agents-md) and [approvals/security documentation](https://learn.chatgpt.com/docs/agent-approvals-security).