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.
git clone --depth 1 https://github.com/cukas/claudes-ai-buddiesWrote 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/cukas/claudes-ai-buddies/buddy-help)<a href="https://agentmods.dev/commands/cukas/claudes-ai-buddies/buddy-help"><img src="https://agentmods.dev/badge/commands/cukas/claudes-ai-buddies/buddy-help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cukas/claudes-ai-buddies/buddy-help"><img src="https://agentmods.dev/badge/commands/cukas/claudes-ai-buddies/buddy-help.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00011 | $0.01497 |
| Opus 5 | $0.00005 | $0.00749 |
| Sonnet 5 | $0.00002 | $0.00299 |
| Haiku 4.5 | $0.00001 | $0.00150 |
Grade A, and why
buddy-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 9d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Buddies v3.1 — Help & Reference
Available Skills
| Skill | Engine | Description |
|---|---|---|
/codex "prompt" |
Codex | Ask Codex anything — brainstorm, delegate, second opinion |
/codex-review |
Codex | Code review via Codex (uncommitted, branch, commit) |
/gemini "prompt" |
Gemini | Ask Gemini anything — brainstorm, delegate, second opinion |
/gemini-review |
Gemini | Code review via Gemini (uncommitted, branch, commit) |
/opencode "prompt" |
OpenCode | Ask OpenCode anything — multi-provider, configurable model |
/opencode-review |
OpenCode | Code review via OpenCode (uncommitted, branch, commit) |
/brainstorm "topic" |
All | Multi-AI roundtable — all available buddies assess the task |
/forge "task" --fitness "cmd" |
All | Competitive build — buddies build, automated scoring picks winner |
/tribunal "question" |
2+ | Adversarial debate — FOR vs AGAINST with evidence |
/tribunal --socratic |
2+ | Socratic — probe assumptions, Claude synthesizes |
/tribunal --steelman |
2+ | Steelman — argue other side's strongest case |
/tribunal --red-team |
2+ | Red-team — attack from multiple angles |
/tribunal --synthesis |
2+ | Synthesis — propose solutions, then hybridize |
/tribunal --postmortem |
2+ | Postmortem — investigate failure from different angles |
/leaderboard |
— | Show ELO ratings leaderboard |
/add-buddy |
— | Register a new AI CLI as a buddy |
/buddy-help |
— | This help reference |
Dynamic Buddy Registry (v3)
Any CLI-based AI tool can become a buddy. Builtin buddies (Claude, Codex, Gemini, OpenCode) are auto-detected. Register custom buddies with /add-buddy:
/add-buddy --id aider --binary aider --display "Aider" --modes exec
Buddy definitions are stored as JSON:
- Builtin:
<plugin>/buddies/builtin/*.json - User:
~/.claudes-ai-buddies/buddies/*.json
Configuration
Config file: ~/.claudes-ai-buddies/config.json
General
| Key | Default | Description |
|---|---|---|
timeout |
120 |
Max seconds per call |
sandbox |
full-auto |
Sandbox mode (full-auto or suggest) |
debug |
false |
Enable debug logging |
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.
- 9d ago First seen · 145 lines · 11 tokens per session scan A 3fda196ec9e4
buddy-help is a command published in the GitHub repository cukas/claudes-ai-buddies (9 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,497 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
brainstorm
Turn a fuzzy idea into a concrete design doc through guided Q&A.
tts-status
Show current TTS plugin status.
tts-setup
Set up TTS with a provider (elevenlabs, openai, google, amazon, azure, edge, kitten, tada, fish, gemini, local).
tts-off
Disable text-to-speech for Claude responses.
tts-on
Enable text-to-speech for Claude responses.
tts-stop
Stop TTS playback immediately.