Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/kingsj0405/ClaudeCODEXaoneWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/kingsj0405/claudecodexaone/council)<a href="https://agentmods.dev/commands/kingsj0405/claudecodexaone/council"><img src="https://agentmods.dev/badge/commands/kingsj0405/claudecodexaone/council/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kingsj0405/claudecodexaone/council"><img src="https://agentmods.dev/badge/commands/kingsj0405/claudecodexaone/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01918 |
| Opus 5 | $0.00020 | $0.00959 |
| Sonnet 5 | $0.00008 | $0.00384 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
council scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage: /council [--mode discuss|critique|plan] [--rounds N] [--roster codex,kexaone,claude-self] [--no-stop] <topic-or-question>
Defaults:
--mode discuss(divergent brainstorming)--rounds 1(run one round, then check in with the user;--no-stopproceeds automatically)--roster codex,kexaone(two members + moderator = you)
Roster key → subagent mapping
| roster key | subagent_type | model / source | requires |
|---|---|---|---|
codex |
codex:codex-rescue |
Codex | the codex plugin from the openai-codex marketplace |
kexaone |
exaone-friendli:k-exaone |
K-EXAONE 236B / FriendliAI | the exaone-friendli plugin in this repo + a Friendli token |
claude-self |
general-purpose |
Claude, fresh context | nothing |
claude-self is a Claude subagent with no memory of this conversation. It is a genuinely useful
member — it reads the prompt cold, so it catches assumptions the moderator has already absorbed —
but it is not an independent model. When the roster is claude-self alone, say so plainly in the
synthesis rather than presenting it as a multi-model result.
If a plugin is not installed, the corresponding subagent_type will not resolve. Drop that member, warn once, and continue with the rest.
Modes
| mode | purpose | flow |
|---|---|---|
discuss |
brainstorming, generating options | each member answers independently → moderator synthesizes |
critique |
sharpening a draft | attach draft → each member critiques + offers alternatives → moderator proposes a merge |
plan |
reviewing an implementation plan | attach plan → each member names risks and gaps → moderator revises |
Output
Each round is written to output/council-{YYMMDD-HHMM}-{slug}/round-{N}.md:
# Round N — {mode}
## Prompt
...
## Codex
...
## K-EXAONE
...
## Moderator Synthesis
...
## User Decision
(next round / finish / revised instruction)
Session state lives in .claude/council-state.json — current session dir, round number, mode,
roster, and the previous synthesis. This is what lets a council survive /clear.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 166 lines · 40 tokens per session scan A 567c5c89b6c0
council is a command published in the GitHub repository kingsj0405/ClaudeCODEXaone (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,918 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).
requirement-review
A command that has several specialized agents review a requirements document and produce a revised version through a controlled workflow.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.