[skills] Add auto-capture-codex adapter

[eazene]

Contribution Type

• Skill (/skills)

What does this do?

Adds auto-capture-codex — the Codex CLI sibling of auto-capture-claude-code. It automatically captures Codex sessions to Open Brain at session end.

Why a separate adapter: Codex stores transcripts as "rollout" JSONL (event_msg records with payload.type == "user_message"/"agent_message") — a different schema from Claude Code. The Claude Code adapter parses zero turns from a Codex rollout and silently captures nothing, so Codex needs its own parser.

Design notes:

• Codex has no SessionEnd event, so the hook runs on Stop and uses a debounced, per-session state-guarded capture to fire once (~120s after the last turn), approximating session end.
• Resolves the rollout transcript by session_id (Codex embeds it in the rollout filename), with stdin-path and newest-rollout-for-cwd fallbacks.
• Caps the payload at 24k chars to stay under the ingest embedding model's ~8191-token limit (oversized payloads otherwise fail HTTP 500).

Requirements

Codex CLI, Node.js 18+, a deployed Open Brain (open-brain-rest /ingest + MCP_ACCESS_KEY). Depends on the auto-capture skill (declared in metadata). No new dependencies.

Checklist

• I've read CONTRIBUTING.md
• README.md with prerequisites, step-by-step install, and expected outcome
• metadata.json has all required fields
• Depends on auto-capture; declared in metadata and linked in the README
• Tested on my own Open Brain instance (real rollout parses to N turns; oversized session truncated to <24k and captured HTTP 200; debounced deferred path verified)
• No credentials, API keys, or secrets are included

🤖 Generated with Claude Code

[github-actions]

OB1 PR Gate

✅ Folder structure — All files are in allowed directories
✅ Required files — README.md and metadata.json found in all contribution folders
✅ Metadata valid — All metadata.json files passed JSON Schema validation
✅ No credentials — No API keys, tokens, or secrets detected
✅ SQL safety — No destructive SQL or core table modifications
✅ Category artifacts — Required file types present for each category
✅ PR format — Title follows [category] Description format
✅ No binary blobs — No oversized or binary files
✅ README completeness — All READMEs include Prerequisites, Steps, and Expected Outcome
✅ Contribution dependencies — All declared skill and primitive dependencies exist and are linked in README
✅ LLM clarity review — Covered by Claude PR Review workflow
✅ Remote MCP pattern — No local MCP server patterns detected — uses remote MCP correctly
✅ Tool audit link — Extensions/integrations link to the MCP Tool Audit guide
✅ Scope check — All changes are within the contribution folder(s)
✅ Internal links — All relative links in READMEs resolve to existing files

Result: All 15 checks passed! Ready for human review.

---

Post-Merge Tasks

These don't block merge — they're reminders for admins after this PR lands.

• Add Auto-Capture Codex Adapter to skills/README.md
• Add Auto-Capture Codex Adapter to root README.md community contributions section
• Add Ezana Azene (@eazene) to CONTRIBUTORS.md
• Post in OB1 Discord #show-and-tell