Codex History Ingest for Obsidian

Mines Codex CLI session rollouts from ~/.codex and distills them into topic-based knowledge pages in an Obsidian vault.

AutomationIntermediate★ 3,691⑂ 371AI score 8/10Last updated: Nov 5, 2026

What it does

Surveys ~/.codex/session_index.jsonl, sessions/**/rollout-*.jsonl and history.jsonl, diffing against .manifest.json so only new or modified files are processed (append mode) — or everything (full mode).
Parses JSONL event envelopes, keeping user intent and assistant output while filtering out token accounting, tool plumbing and repeated plan snapshots.
Applies a privacy filter: strips API keys, tokens and credentials, and summarizes rather than quoting raw transcripts.
Clusters by topic instead of by session, routing content into projects/, concepts/, skills/, entities/, synthesis/.
Stamps pages with summary, base_confidence, lifecycle and provenance frontmatter plus ^[extracted] / ^[inferred] / ^[ambiguous] markers.
Updates the manifest and runs a single locked obsidian-wiki memory sync call to refresh index.md, log.md, hot.md, then optionally refreshes the QMD search index.

Who it's for

Heavy Codex CLI users whose session history piles up unused.
Obsidian "second brain" owners who want AI work turned into durable notes.
Engineers juggling multiple repos who want recurring debug playbooks and decisions captured.

Usage examples

"Sync this week's Codex sessions into my wiki" → append mode reports a delta summary and ingests only new rollouts.
Invoke via the router /wiki-history-ingest codex for a full re-ingest after a wiki-rebuild.
Use cwd metadata from session_meta to create or update projects/<name>/<name>.md architecture notes per project.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/Ar9av/obsidian-wiki/HEAD/skills/codex-history-ingest/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/codex-history-ingest folder from the GitHub repo Ar9av/obsidian-wiki into my ~/.claude/skills/ar9av-codex-history-ingest/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Ar9av/obsidian-wiki.git /tmp/obsidian-wiki && mkdir -p ~/.claude/skills && cp -r /tmp/obsidian-wiki/skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal.
Clone the repo: git clone https://github.com/Ar9av/obsidian-wiki.git /tmp/obsidian-wiki
Create the skills directory: mkdir -p ~/.claude/skills
Copy the skills: cp -r /tmp/obsidian-wiki/skills/* ~/.claude/skills/ — copy the whole set, since this skill references llm-wiki/SKILL.md and its references.
Configure OBSIDIAN_VAULT_PATH in a .env file or the global config, and CODEX_HISTORY_PATH if your Codex data is not in ~/.codex.
Install the obsidian-wiki CLI as documented in the repo (required for the locked memory sync). Optionally install the qmd CLI and set QMD_WIKI_COLLECTION for search indexing.
Restart Claude Code and ask: "Ingest my Codex session history into the Obsidian wiki."
Run the first ingest against a backup or test vault so you can review redaction and page routing before trusting it on your main vault.

View source on GitHub ↗License: MIT