codex-export-moreExport a Codex CLI or Codex Desktop (App) session to Markdown, HTML, or Obsidian notes. Use when the user asks to export, save, share, or review a past chat, session, or transcript. Supports --brief, --redact, --since/--until, --grep, --append (incremental), --interactive (message picker), --sessions (merge), --watch (auto-incremental), and --list. Works with both Codex CLI and Codex Desktop app sessions.
Install via ClawdBot CLI:
clawdbot install sb679/codex-export-moreGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/sb679/codex-export-more/actions/workflows/ci.yml/badge.svgAudited Sep 10, 2026 · audit v1.0
Generated Sep 10, 2026
An indie developer uses Codex CLI to build a feature and wants to turn the session into a readable narrative for their technical blog. They run codex-export with --brief --redact to strip tool outputs and sensitive paths, then paste the Markdown into their CMS. The redaction protects API keys and local paths before publishing.
An SRE team uses Codex sessions to investigate a production outage and needs a durable, reviewable record for the incident postmortem. They export the relevant session with --since/--until to isolate the incident window and --append in watch mode to keep the transcript current during the investigation. The resulting Markdown is attached to the postmortem ticket.
A documentation specialist merges several Codex sessions on related tasks into one consolidated reference using --sessions and --grep to pull only turns about a specific topic. They export to Obsidian format so internal wikilinks and tags resolve in the team vault. This turns scattered AI conversations into a searchable internal knowledge asset.
A compliance officer in a regulated environment needs to document how staff used Codex for sensitive workflows without exposing PII or secrets. They use --redact and --list to select sessions by ID, then export to Markdown for archival and review. The checkpoint state from --append allows incremental updates as sessions continue.
An instructor preparing a course uses --interactive to hand-pick the most instructive messages from a Codex session, then exports with --brief to focus on reasoning and code. The clean Markdown becomes a lesson handout or slide source. Watch mode lets them append live coding demos recorded during class.
The core exporter is free and open source, driving adoption among individual developers, while advanced capabilities like org-wide session archiving, policy-based redaction rules, and audit log export are sold as an enterprise add-on. This mirrors common dev-tool monetization where the OSS base builds trust and the enterprise tier captures compliance budgets.
Position codex-export as the bridge between AI coding sessions and tools like Obsidian, Notion, or Confluence, sold as a premium plugin or template bundle. The Obsidian and Markdown focus makes it a natural fit for the personal knowledge management market, where users pay for workflows that reduce manual copy-paste.
Offer the local Python script free, then monetize a cloud dashboard where teams browse, search, share, and annotate exported Codex sessions. Collaboration features like shared workspaces, comment threads, and role-based redaction drive recurring revenue for teams that need visibility into AI-assisted work.
💬 Integration Tip
Start with `--list` to grab a session ID, then do a quick `--brief --redact` export to verify output before automating with `--watch` or `--append`; wrap it in a shell alias or CI step so transcripts are captured consistently without manual commands. Keep the generated `.state.json` checkpoint file alongside the output if you rely on incremental appends.
Scored Sep 10, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.