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.
npx agentmods add commands/tsarihan/model-council-mcp/setupgit clone --depth 1 https://github.com/tsarihan/model-council-mcpWrote 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/tsarihan/model-council-mcp/setup)<a href="https://agentmods.dev/commands/tsarihan/model-council-mcp/setup"><img src="https://agentmods.dev/badge/commands/tsarihan/model-council-mcp/setup.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00449 |
| Opus 5 | $0.00009 | $0.00225 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
setup 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 3d 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.
This is a copy
91% identical to setup — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Help the user set up the model council interactively.
-
Call the
council_statustool first to detect their environment (local Ollama models, cloud reachability, whether the Claude and Codex CLIs are installed and logged in) and see the current council + tiers. -
For each subscription they might want to change, use an interactive selectable menu (AskUserQuestion) so they can pick with arrow keys — only ask about ones that are relevant (e.g. don't push a Claude tier if the Claude CLI isn't installed):
- Claude:
free·pro·max5x·max20x - ChatGPT:
free·plus·pro5x·pro20x - Ollama:
free·pro·maxFree = no cloud/subscription members for that provider. Higher tiers raise that provider's concurrency limit.
- Claude:
-
Call
setup_councilwith the chosen tiers. Then show the user:- the resulting council members (grouped by provider) and the total count,
- the quota warning (these members use their own subscription quotas),
- any hints from
council_status(e.g. "Codex CLI installed but not signed in — runcodex login"), - and that a
/reload-pluginsis needed for concurrency / newly-enabled providers to take full effect.
Keep it friendly and concise. If they want to trim the council, remind them configure_council can remove members and the change persists.
Always write model IDs in full and verbatim as they appear in the tool output — in particular the Codex members are gpt-5.6-sol, gpt-5.6-luna, and gpt-5.6-terra. Never abbreviate them to sol / luna / terra (the bare names are invalid for a ChatGPT account and are confusing to the user).
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.
- 3d ago First seen · 24 lines · 17 tokens per session scan A 28481d70641c
setup is a command published in the GitHub repository tsarihan/model-council-mcp (1 stars, last pushed 29d ago), licensed Apache-2.0. It adds 17 tokens to every session and 449 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to setup, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.