read-codex-history
An agent skill by daymade, from daymade/claude-code-skills. Tags: analysis, documentation, history, local-workflow, search.
What it does
Reads, searches, and exports local OpenAI Codex history without continuing the old task. Lists recent Codex sessions, extracts exact prompt-ledger inputs by Session, locates a rollout by verified session_meta identity, reconstructs one chronological user/assistant timeline with fork and compaction lineage, and performs bounded keyword search across live and archived rollouts. Use whenever the user asks what they told Codex, wants recent original inputs, a Codex Session ID, full prior context, fork ancestry, or evidence of what a Codex run did. For Claude Code history use read-claude-code-history.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add daymade/claude-code-skills --skill read-codex-historyOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-claude-code/read-codex-history ~/.claude/skills/read-codex-historySafety box score
Grade C, moderate risk: 37 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a read-only local-history tool for Claude Code, Codex, and Kimi stores, with a strong focus on exact verbatim inputs, session lineage, and rollback/evidence reconstruction. The main risks are broad access to private local history stores and the fact that several key implementation files were not readable in this review.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It is designed to run bundled local scripts and SQLite queries, e.g. `python scripts/reconcile_codex_inputs.py --session <exact-id> --format json` and the `scripts/prompt_cursor.py` CLI. |
| Network access | 0 (none) | I found no network fetches or remote posts; the reviewed files only read local history stores and local SQLite databases. |
| Filesystem reach | 2 (moderate) | It reads outside the project into home-scoped stores such as `~/.codex/history.jsonl`, `~/.claude/history-sources.json`, `~/.kimi-code/`, and `~/.claude-flow-viewer/search.sqlite`. |
| Secrets & credentials | 2 (moderate) | The skill intentionally exposes exact prompt-history and session evidence; `references/storage_and_portability.md` says verbatim Codex input mode may contain "credentials or private business context." |
| Privilege & persistence | 0 (none) | No sudo, services, global installs, shell startup edits, or other privilege-changing actions appeared in the reviewed files. |
| Instruction hijack surface | 1 (low) | The reviewed text is highly directive, but I did not find explicit attempts to bypass confirmations, ignore higher-priority instructions, or fetch external instructions to follow. |
| Irreversible actions | 0 (none) | It is read-only by design and does not send messages, deploy, publish, delete, or otherwise act on behalf of the user. |
| Transparency | 2 (moderate) | Several core files could not be read, including `scripts/read_codex_session.py`, `scripts/analyze_sessions.py`, `scripts/list_local_history.py`, `scripts/reconcile_codex_inputs.py`, and `scripts/_core/text.py`, so key behavior is only partially inspectable. |
Before installing
- Read `scripts/prompt_cursor.py` first if you plan to use the current-thread cursor; it reads `~/.codex/history.jsonl`.
- Decide whether you are comfortable exposing exact verbatim Codex inputs, not summaries, from local history stores.
- Check whether you want cross-provider home discovery and archive registry access, or only a single explicit store.
Rated 2026-10-19 by an automated review of 22 files from the skill's repository.
Source
- Repository
- daymade/claude-code-skills (all skills from this repository)
- Path
- daymade-claude-code/read-codex-history/SKILL.md
- Branch
- main
- Updated
- 2026-09-20
Related skills
- read-claude-code-history — Reads, searches, and exports local Claude Code history without resuming work.
- recall — Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents).
- local-conversation-history — Entry point for local AI conversation history across providers.
- audit-prep-assistant — Prepares codebases for security review using Trail of Bits' checklist.
- automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
- competitors — When the user wants to create competitor comparison or alternative pages for SEO and sales enablement.