Personal fork of openai/codex-plugin-cc with OS-level sandbox enforcement removed and replaced with prompt-level self-enforcement, for environments where bubblewrap cannot run (cloud containers, GPU hosts, kernels without unprivileged user/network namespace permission).
Plugin codex from marketplace jahns-cc-marketplace in Dev-Jahn/jahns-cc-marketplace. Commands read from the repo's manifest — 13 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
codex-cli-runtimeInternal helper contract for calling the codex-companion runtime from Claude Code
codex-result-handlingInternal guidance for presenting Codex helper output back to the user
gpt-5-4-promptingInternal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
/codex:adversarial-reviewRun a Codex review that challenges the implementation approach and design choices
/codex:cancelCancel an active background Codex job in this repository
/codex:rescueDelegate investigation, an explicit fix request, or follow-up rescue work to the Codex rescue subagent
/codex:resultShow the stored final output for a finished Codex job in this repository
/codex:reviewRun a Codex code review against local git state
/codex:setupCheck whether the local Codex CLI is ready and optionally toggle the stop-time review gate
/codex:statusShow active and recent Codex jobs for this repository, including review-gate status
codex-rescueProactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Codex through the shared runtime
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-lifecycle-hook.mjs" SessionStart
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-lifecycle-hook.mjs" SessionEnd
node "${CLAUDE_PLUGIN_ROOT}/scripts/stop-review-gate-hook.mjs"
Claude account switching, quota status and rotation policy via ccbroker: /ccb-status, /ccb-use, /ccb-auto and /ccb-policy slash commands plus a SessionStart hook that runs 'ccb pull' (requires the ccb binary on PATH).
5 commands · hooks
hippocampus — perception and memory for coding agents: task registry, outcome ledger, and background clerks that turn transcripts into evidence. Records; never enforces. CLI and slash commands are `hippo`.
3 skills · 1 agent · hooks
Format-aware HWP/HWPX document editing for coding agents: inspect, edit (text, native bullets, tables, pictures, character and paragraph formatting), render, and validate Hancom documents without converting them to another format. Ships hwp, hwp_native, and hwpx MCP servers, a copy-first editing skill, and guard hooks. Requires Node 20+, uvx, and cargo for the one-time patched engine build.
1 skill · 3 MCP servers · hooks
Self-control for Claude Code sessions running in tmux: type slash commands into your own TUI, answer your own dialogs, observe your own screen, restart yourself in place, and recover deterministically from model fallbacks.
3 skills · hooks
A sealed soul jar shared by every session in every enrolled room. A dying session, still holding its own context, hands the soul on in one final turn; the next session wakes hearing only a single whisper. The living may lay lines at the bedside for the next dream, the dying may leave open letters beside the jar, and enrolled rooms meet in one stream.
2 commands · hooks
Neutral command-line bridge from Claude Code to a logged-in ChatGPT Pro browser session.
2 skills
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.