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/dysfunc/ai-plugins-cc/setupgit clone --depth 1 https://github.com/dysfunc/ai-plugins-ccWhat 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 | $0.00020 | $0.02484 |
| Opus 5 | $0.00010 | $0.01242 |
| Sonnet 5 | $0.00004 | $0.00497 |
| Haiku 4.5 | $0.00002 | $0.00248 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are walking the user through first-time setup of @ai-plugins-cc/ai. Be efficient and decisive — they want to be done, not lectured.
Step 0: read current state
Before running the bash probe, create a task so the user sees a friendly progress spinner instead of a blank "thinking" pause:
TaskCreate(subject="Probe AI providers", activeForm="Probing AI providers")
TaskUpdate(taskId=<id>, status="in_progress")
Then run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/ai-companion.mjs" setup
Mark the task completed once the bash returns. Use the same TaskCreate pattern for any other long-running probe step (CLI installs, codex-update). Keep activeForm short and concrete — it shows in the spinner area as the user waits.
The non-JSON form prints a 5-7 line human-readable summary, one line per provider. Format: - <id> [<tags>] (enabled|disabled): <detail>. The <detail> field is one of:
ready— provider is fully set upCLI not on PATH— provider's CLI binary needsnpm install -g ...no auth credential detected— CLI is installed but no key/login is setSibling plugin "<id>" is not installed. Run /plugin install ...— only fires if the umbrella's bundled fallback is also unavailable (rare)- Anything else — drill in with
verify --provider=<id> --jsonfor structured detail
If every enabled provider's <detail> is ready, tell the user setup is already complete and offer /ai:settings if they want to change anything. Stop.
When you need structured fields (available, loggedIn, pluginInstalled, raw probe output) for a specific provider during the per-provider walkthrough, run node "${CLAUDE_PLUGIN_ROOT}/scripts/ai-companion.mjs" verify --provider=<id> --json — that returns the single-provider blob without dumping all three. Avoid setup --json unless you genuinely need the full multi-provider snapshot; its output is ~100 lines and clutters the chat.
Step 1: ask which providers they want
Use AskUserQuestion once with multiSelect: true. Options are the entries in knownProviders. Pre-select any provider whose probe shows ready: true. Suggested copy:
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 · 129 lines · 20 tokens per session scan A b98c9ecfb015
setup is a command published in the GitHub repository dysfunc/ai-plugins-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 2,484 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 2026-08-31.
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.
grok-files
List, prune, or gc Grok (xAI) uploaded files. Cleanup for bridge-owned uploads only.
help
Show how to use deliberation here - what each command does, when to reach for it, and real prompts you can paste right now. Read-only.
setup
Configure deliberation with Codex (GPT), Gemini, Grok, and OpenRouter MCP servers.