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/altimateai/claude-consensus/consensus-setupgit clone --depth 1 https://github.com/AltimateAI/claude-consensusWhat 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 | $0.00016 | $0.03278 |
| Opus 5 | $0.00008 | $0.01639 |
| Sonnet 5 | $0.00003 | $0.00656 |
| Haiku 4.5 | $0.00002 | $0.00328 |
Grade B, and why
consensus-setup scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f ~/.claude/.env ] && grep -q 'OPENROUTER_API_KEY=.\+' ~/.claude/.env && echo "KEY_FOUND" || echo "KEY_MISSING" How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consensus Setup Wizard
Interactive setup to configure which AI models participate in /code-review and /plan-review.
Step 1: Check for Existing Config
Check if ~/.claude/consensus.json exists using the Read tool.
If it exists, show the user what's currently configured (list enabled models and quorum), then ask:
AskUserQuestion:
question: "An existing consensus config was found. What would you like to do?"
header: "Config"
options:
- label: "Reconfigure"
description: "Start fresh — replace the existing config with new settings"
- label: "Keep current"
description: "Exit setup and keep the current configuration"
If user chooses "Keep current", print the current config summary and stop.
Step 2: Auto-Detect CLIs
Run all of these checks in parallel via Bash:
command -v pi && echo "PI_OK" || echo "PI_MISSING"
command -v codex && echo "CODEX_OK" || echo "CODEX_MISSING"
command -v agy && echo "AGY_OK" || echo "AGY_MISSING"
command -v qwen && echo "QWEN_OK" || echo "QWEN_MISSING"
Also check for an existing OpenRouter API key (verify it's non-empty):
[ -f ~/.claude/.env ] && grep -q 'OPENROUTER_API_KEY=.\+' ~/.claude/.env && echo "KEY_FOUND" || echo "KEY_MISSING"
Report findings to the user:
## CLI Detection Results
- pi CLI: {installed / not found}
- Codex CLI: {installed / not found}
- Antigravity CLI (`agy`): {installed / not found}
- Qwen CLI: {installed / not found}
- OpenRouter API key: {found in ~/.claude/.env / not found}
Step 3: Provider Choice
AskUserQuestion:
question: "How do you want to connect to external models?"
header: "Provider"
options:
- label: "OpenRouter (Recommended)"
description: "1 API key, all 9 models via pi. Simplest setup."
- label: "Native CLIs"
description: "Use codex, Antigravity (`agy`), and qwen CLIs directly where available. Requires each CLI installed separately."
- label: "Both"
description: "Mix and match — use native CLIs where available, OpenRouter/pi for the rest."
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 · 308 lines · 16 tokens per session scan B c751dcc701a7
consensus-setup is a command published in the GitHub repository AltimateAI/claude-consensus (32 stars, last pushed 8d ago), licensed MIT. It adds 16 tokens to every session and 3,278 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.