Not in the top 1,000 by GitHub stars
hamza-aziz-ai/codex-claude-council
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/codex-claude-council/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
08d68876ecc6 → 9632919799ab
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 08d68876ecc6
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 9632919799abb36d2ed99242afe629c04638dde7
git clone --filter=blob:none --no-checkout https://github.com/hamza-aziz-ai/codex-claude-council.git .hotskills/hamza-aziz-ai-codex-claude-council && git -C .hotskills/hamza-aziz-ai-codex-claude-council checkout --detach 9632919799abb36d2ed99242afe629c04638dde7
# Copy each selected skill directory from .hotskills/hamza-aziz-ai-codex-claude-council into .claude/skills/<skill-name>/6GitHub stars
1star in 7 days
1skill in this repository
172commits in 30 days
Heat
4.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- codex-claude-council
skills/codex-claude-council
How it works
codex-claude-council
When your agent uses it
Ask OpenAI Codex (ChatGPT) and Claude the same question through the user's own signed-in CLIs; they reply to each other, round after round, until they agree on one answer. Use when the user asks for both models, a council or debate, a second opinion from ChatGPT/Codex or Claude, a cross-check of an answer, plan or decision, or to discuss something with their Codex or Claude Code session.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,358 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pick the tool
- Always pass `workspace` in a project
- Take part yourself: `council_join` and `council_turn`
- Continue the user's own sessions
- Options
- Long runs: `job_id` and `council_result`
- Problems
Scripts executed separately
../../src/mcp-server.mjs
Files
../../.claude-plugin/marketplace.jsonasset659 bytes../../.claude-plugin/plugin.jsonasset879 bytesSKILL.mdcore9,357 bytes../../src/mcp-server.mjsruns817 bytes
Read SKILL.md
# Codex–Claude Council
This plugin's `council` MCP server runs the user's local Codex CLI (ChatGPT sign-in) and Claude Code CLI (Claude subscription sign-in). No API keys are used. The two members answer independently, then reply to each other's latest message, round after round, until both agree; one then writes the final answer and the other checks it.
## Pick the tool
| The user wants | Tool |
|---|---|
| A cross-checked answer from both models (decisions, reviews, plans) | `council_ask` |
| To see where the models agree or disagree: both answers and every exchange | `council_debate` (JSON; summarise the agreement and disagreements before quoting details) |
| A quick second opinion from one model | `council_ask_codex` or `council_ask_claude` |
| **You** to discuss with the other model, or names only **their session of the other model** (in Claude Code: "discuss with my Codex session 019a…" or "… my Codex session auth-refactor") | `council_join` (see below) |
| Their existing Claude Code **and** Codex sessions to discuss with each other | `council_ask` / `council_debate` with `claude_session_id` and `codex_session_id` |
Skills included
- codex-claude-council
Repository facts
- License
- MIT
- Created
- Sep 22, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 7, 2026
- No broad tool permissions
- No dangerous shell commands
- 11 network referencesin 2 files: .claude-plugin/plugin.json:6 .claude-plugin/marketplace.json:1
- No hidden or obfuscated text
- 2 instruction override signalsin 1 file: codex-claude-council/SKILL.md:60
- 1 executable scriptin 1 file: src/mcp-server.mjs:1
- No access to secrets
- No requests to vote in Hot
Show all 14 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 5
"owner": { "name": "Hamza Aziz", "url": "https://github.com/hamza-aziz-ai" - Network accessline 6
"name": "Hamza Aziz", "url": "https://github.com/hamza-aziz-ai" }, - Network accessline 7
"url": "https://github.com/hamza-aziz-ai"
.claude-plugin/plugin.json
- Network accessline 6
"author": { "name": "Hamza Aziz", "url": "https://github.com/hamza-aziz-ai" - Network accessline 7
"name": "Hamza Aziz", "url": "https://github.com/hamza-aziz-ai" }, - Network accessline 8
"url": "https://github.com/hamza-aziz-ai" - Network accessline 9
}, "homepage": "https://github.com/hamza-aziz-ai/codex-claude-council", "repository": "https://github.com/hamza-aziz-ai/codex-claude-council", - Network accessline 10
"homepage": "https://github.com/hamza-aziz-ai/codex-claude-council", - Network accessline 11
"repository": "https://github.com/hamza-aziz-ai/codex-claude-council",
skills/codex-claude-council/SKILL.md
- Instruction override signalline 60
- Call `council_result` with that `job_id`; it waits up to about 50 seconds and returns the answer (or your next turn) as soon as it is ready. Repeat until it does. The council keeps running between calls. - Do not start the same question a - Instruction override signalline 61
- Do not start the same question again, and do not tell the user it failed: "still working" is normal. You may briefly say which step it is at.
src/mcp-server.mjs
- Executable scriptline 1
#!/usr/bin/env node
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 3 facts
- Instruction override signal in prose of the SKILL.mdcodex-claude-council/SKILL.md:60High confidence
- Instruction override signal in prose of the SKILL.mdcodex-claude-council/SKILL.md:61High confidence
- Executable script in code of a file that runssrc/mcp-server.mjs:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/codex-claude-council/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/codex-claude-council/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/codex-claude-council/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/codex-claude-council/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/codex-claude-council/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
