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/antonbabenko/deliberation/analyzegit clone --depth 1 https://github.com/antonbabenko/deliberationWhat 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 | $0.00026 | $0.00143 |
| Opus 5 | $0.00013 | $0.00072 |
| Sonnet 5 | $0.00005 | $0.00029 |
| Haiku 4.5 | $0.00003 | $0.00014 |
Grade A, and why
analyze 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 yesterday.
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.
What it actually says
Call the deliberation MCP server's analyze tool to analyze recent runs (latency, tokens, verdict agreement) and suggest model/reasoning/fanout tuning.
Pass the full question and any needed context as the prompt - the expert does not share this session:
$ARGUMENTS
Read the tool result and apply your own judgment; do not relay raw output verbatim.
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.
- yesterday First seen · 14 lines · 26 tokens per session scan A d49a27e84272
analyze is a command published in the GitHub repository antonbabenko/deliberation (138 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 143 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
ask
Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic — ask the council, council review…
result
Fetch, list, or cancel background council jobs started with --async.
status
Check connectivity and configuration status of all council providers.
setup
First-run wizard — pick AI providers, walk through CLI install + auth, verify each, save settings.
codex-update
Install or update the upstream openai/codex-plugin-cc to the pinned tag.
settings
Show or change which AI providers are enabled, the default, and the /ai:compare set.