openai/codex-plugin-cc

Use Codex from Claude Code to review code or delegate tasks.

Stars: 33.4k
Forks: 2.3k
Open beginner issues: 0
Indexed issues: 263

Dominant language: JavaScript
License: Apache-2.0
Last GitHub push: Jul 8, 2026
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

263 open issues indexed

Stop review gate has no way to pin the model or reasoning effort it reviews with Open

Difficulty 3/5 1-2 days Newbie friendliness 76/100

openai/codex-plugin-cc#769 · Opened Sep 18, 2026
SessionEnd never reclaims the app-server broker when the Claude session cwd is not a git repository Open

Difficulty 4/5 3-5 days Newbie friendliness 56/100

openai/codex-plugin-cc#767 · Opened Sep 16, 2026
Stop-review gate: review timeout equals the hook's own 900s timeout, so a slow review ends the turn with no message Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

openai/codex-plugin-cc#766 · Opened Sep 16, 2026
codex-rescue with --cwd <git worktree>: git write ops fail because the linked worktree's gitdir (hub .git/worktrees/<name>) is outside the sandbox writable roots Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

openai/codex-plugin-cc#765 · Opened Sep 15, 2026
Stop-review gate is lost in every new git worktree (state keyed by rev-parse --show-toplevel) Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#764 · Opened Sep 14, 2026
Consider whether the "adversarial review" framing can be softened Open

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

openai/codex-plugin-cc#760 · Opened Sep 14, 2026
A server-side turn failure that terminates stores no `errorMessage`, so `status` reports the reason as `Summary: {` Open

Difficulty 3/5 1-2 days Newbie friendliness 74/100

openai/codex-plugin-cc#757 · Opened Sep 12, 2026
codex-rescue reports completion without checking git state — reproducible false positives Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#754 · Opened Sep 8, 2026
ensureBrokerSession() deletes a live broker's state without killing it — the only production caller passes no killProcess Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#753 · Opened Sep 8, 2026
`VALID_REASONING_EFFORTS` rejects `max` and `ultra` locally, so the flagship model's top two reasoning tiers are unreachable from the plugin Open

Difficulty 2/5 1-3 hours Newbie friendliness 64/100

openai/codex-plugin-cc#751 · 1 comment · 1 reaction · Opened Sep 8, 2026
`/codex:transfer` is one-shot per session: a second run silently imports nothing, and is indistinguishable from failure Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

openai/codex-plugin-cc#750 · Opened Sep 7, 2026
Alternative: claude-codex-bridge — full async Codex agents with live progress & steering Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

openai/codex-plugin-cc#745 · Opened Sep 6, 2026
`runCommand` sets `maxBuffer: options.maxBuffer` — the ENOBUFS fix from #179 works only because a spread `undefined` deletes Node's default Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

openai/codex-plugin-cc#744 · 2 comments · Opened Sep 5, 2026
SessionEnd kills whatever pid `broker.json` names, without checking it is still a broker (pid reuse → SIGTERM to an unrelated process group) Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

openai/codex-plugin-cc#743 · Opened Sep 5, 2026
`npm test` leaves a detached broker and a fake app-server behind for every test workspace Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#741 · Opened Sep 5, 2026
`thread/resume` sandbox is ignored while the thread is still live in the shared app-server, so `task --resume-last --write` cannot write after a read-only run Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

openai/codex-plugin-cc#740 · Opened Sep 5, 2026
Codex history shows <recommended_plugins> instead of session titles Open

Difficulty 3/5 1-2 days Newbie friendliness 58/100

openai/codex-plugin-cc#726 · 1 comment · Opened Sep 4, 2026
/codex:transfer is broken when CLAUDE_CONFIG_DIR is set — Claude transcript root hardcoded to ~/.claude/projects Open

Difficulty 4/5 3-5 days Newbie friendliness 50/100

openai/codex-plugin-cc#721 · Opened Sep 4, 2026
Windows: every command leaks an orphaned broker, and a live app-server makes the workspace directory undeletable Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#718 · 3 comments · Opened Sep 3, 2026
DEP0190 on Node 24: every companion command warns on stderr before its JSON Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

openai/codex-plugin-cc#717 · Opened Sep 2, 2026
Windows: `cancel` silently fails — Git Bash mangles `taskkill /PID /T /F` flags, leaving jobs stuck as `running` Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#708 · Opened Sep 2, 2026
App-server broker retains thread subscriptions after task clients disconnect Open

Difficulty 4/5 3-5 days Newbie friendliness 68/100

openai/codex-plugin-cc#706 · 1 comment · Opened Sep 1, 2026
adversarial-review threads are always ephemeral — no way to verify which model actually ran a review Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

openai/codex-plugin-cc#705 · Opened Aug 31, 2026
status reports a background job as running forever when its worker dies before writing a terminal status Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

openai/codex-plugin-cc#704 · Opened Aug 31, 2026
Skill `gpt-5-4-prompting` still targets GPT-5.4, retired from the rate card on 2026-08-31 Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#703 · Opened Aug 30, 2026
task: add `--resume-thread <id>` — jobs killed by a usage limit cannot be resumed from the plugin Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

openai/codex-plugin-cc#700 · Opened Aug 30, 2026
Background jobs: prompt text swallowed as options (-m pytest -> model 404); dead workers never finalized; cancel hangs; stderr discarded Open

Difficulty 5/5 Over a week Newbie friendliness 45/100

openai/codex-plugin-cc#699 · Opened Aug 29, 2026
`captureTurn` treats the `error` notification as non-terminal, so a Codex-side failure hangs the turn forever and wedges the job at `status: running` Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#698 · 1 comment · Opened Aug 29, 2026
app-server-broker silently disables all git hooks when started in a git worktree Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#697 · Opened Aug 28, 2026
Stop-review gate discards the failure reason on four paths; every failure surfaces as a DEP0190 warning Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#695 · 1 comment · Opened Aug 27, 2026
review / adversarial-review forward --model unnormalized, so the documented `spark` alias fails as "not supported when using Codex with a ChatGPT account" Open

Difficulty 2/5 1-3 hours Newbie friendliness 86/100

openai/codex-plugin-cc#687 · 3 comments · Opened Aug 26, 2026
`codex-rescue` can generate duplicate `pgrep -f "codex-companion.mjs"` wait loops that keep each other alive on macOS (stuck background tasks) Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#686 · Opened Aug 26, 2026
`/codex:setup --enable-review-gate` reports success but writes the flag to a state root the Stop hook never reads — the gate silently fails open Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#684 · 2 comments · Opened Aug 25, 2026
review --json emits no `result` (and no `parseError`): the built-in reviewer path never produces schema-shaped output, unlike adversarial-review Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#679 · Opened Aug 24, 2026
Stop review gate fails open when hook stdin is malformed JSON Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

openai/codex-plugin-cc#676 · Opened Aug 23, 2026
Review commands start ephemeral threads, so Codex usage from them is unattributable Open

Difficulty 3/5 1-2 days Newbie friendliness 70/100

openai/codex-plugin-cc#675 · Opened Aug 23, 2026
docs(codex-rescue): document the sandbox writable-root constraint (writes outside the repo are silently read as delegation failure) Open

Difficulty 1/5 1-3 hours Newbie friendliness 88/100

openai/codex-plugin-cc#673 · Opened Aug 23, 2026
Shared per-workspace broker is torn down by any session's SessionEnd, killing other sessions' in-flight jobs Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

openai/codex-plugin-cc#671 · Opened Aug 23, 2026
SessionStart hook is killed by its own 5s timeout, silently dropping CODEX_COMPANION_SESSION_ID Open

Difficulty 3/5 1-2 days Newbie friendliness 64/100

openai/codex-plugin-cc#670 · Opened Aug 22, 2026
app-server client never marks itself unusable after child exit — two unbounded hangs in the broker dispatch path (1.0.4) Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

openai/codex-plugin-cc#665 · 3 comments · Opened Aug 21, 2026
SessionStart hook appends to $CLAUDE_ENV_FILE unconditionally — breaks the Bash tool on Windows after ~28 session starts Open

Difficulty 3/5 1-2 days Newbie friendliness 38/100

openai/codex-plugin-cc#664 · 1 comment · Opened Aug 21, 2026
SessionStart hook appends duplicate exports to CLAUDE_ENV_FILE until every Bash call fails Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

openai/codex-plugin-cc#661 · Opened Aug 19, 2026
Companion runs record neither the resolved model nor which `codex` binary served them Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#655 · Opened Aug 17, 2026
Document `--model` on `review` and `adversarial-review` Open

Difficulty 1/5 Under an hour Newbie friendliness 85/100

openai/codex-plugin-cc#654 · Opened Aug 17, 2026
`review --base <nonexistent-sha>` exits 0 and reviews a far wider diff Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#653 · Opened Aug 17, 2026
Add --effort to review/adversarial-review subcommands (parity with task) Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

openai/codex-plugin-cc#651 · Opened Aug 16, 2026
Windows: SHELL env var (Git Bash) breaks taskkill; handleCancel swallows terminateProcessTree exceptions, leaving jobs stuck in running/finalizing Open

Difficulty 4/5 3-5 days Newbie friendliness 68/100

openai/codex-plugin-cc#647 · Opened Aug 14, 2026
Review jobs on Windows leave junk files in the reviewed repo (pwsh treats ">" in quoted code as a redirect) Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#643 · 2 comments · Opened Aug 13, 2026
Plugin never answers MCP tool-call approval requests, so every MCP call in a `task` run is denied Open

Difficulty 4/5 3-5 days Newbie friendliness 58/100

openai/codex-plugin-cc#640 · 1 comment · Opened Aug 13, 2026
result/cancel report "No job found" for jobs that exist; killed workers stay `running` forever Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

openai/codex-plugin-cc#639 · Opened Aug 13, 2026

A short digest of beginner-friendly GitHub issues.