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/helpgit 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 | $0.00033 | $0.00974 |
| Opus 5 | $0.00016 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help
Deliberation gives you a second opinion from GPT, Gemini, Grok, and OpenRouter, without leaving your editor. You ask; they answer independently; Claude reads the answers back to you. The experts advise by default - GPT and Gemini can also make changes when you ask them to.
Step 1: One quick look at your setup (ONE Bash call)
set -u
host="Claude Code"
[ -n "${CURSOR_TRACE_ID:-}${CURSOR:-}" ] && host="Cursor"
[ -n "${KIRO_VERSION:-}${KIRO:-}" ] && host="Kiro"
[ -n "${CODEX_HOME:-}" ] && [ -z "${CLAUDECODE:-}" ] && host="Codex CLI"
echo "Host: $host"
CFG="${DELIBERATION_CONFIG:-${XDG_CONFIG_HOME:-$HOME/.config}/deliberation/config.json}"
case "$CFG" in /*) ;; *) CFG="$HOME/.config/deliberation/config.json";; esac
[ -f "$CFG" ] && echo "Config: found" || echo "Config: missing - run /deliberation:setup first"
[ -n "${XAI_API_KEY:-}" ] && echo "Grok key: set" || echo "Grok key: unset (Grok will skip)"
[ -n "${OPENROUTER_API_KEY:-}" ] && echo "OpenRouter key: set" || echo "OpenRouter key: unset (OpenRouter will skip)"
If the host is not Claude Code, tell the user the commands work the same way but
the exact syntax can differ on their host, and point them at the per-host guides
in the project's public-docs/hosts/. Then show the rest of this guide.
Step 2: Show the guide
Render the sections below. Keep it tight - this is a cheat sheet, not a manual.
What each command is for
| Command | Use it when |
|---|---|
/ask-gpt, /ask-gemini, /ask-grok, /ask-openrouter |
You want one model's take on something. |
/ask-all |
You want several models in parallel and a side-by-side read. |
/consensus |
The decision matters and you want the models to argue to one verdict. |
/deliberation:analyze |
You want to see which models are slow or rarely add anything. |
/deliberation:doctor |
Something looks broken - commands missing, providers failing, empty analyze. |
/deliberation:setup |
First install, or to repair the install. |
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.
- 2d ago First seen · 85 lines · 33 tokens per session scan A ee8d82253dca
help is a command published in the GitHub repository antonbabenko/deliberation (138 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 974 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 2026-08-30.
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.