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/beevibe-ai/beevibe-ctoWrote 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/beevibe-ai/beevibe-cto/decide)<a href="https://agentmods.dev/commands/beevibe-ai/beevibe-cto/decide"><img src="https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/decide/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/beevibe-ai/beevibe-cto/decide"><img src="https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/decide.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 | $0.00054 | $0.05465 |
| Opus 5.5 | $0.00022 | $0.02186 |
| Sonnet 5.5 | $0.00011 | $0.01093 |
| Haiku 4.5 | $0.00005 | $0.00547 |
Grade A, and why
decide 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 2mo 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/adr:decide — Architecture Deep Research
Use when the user is making an architecture decision and wants ADR to run the full pipeline. Trigger phrases: "pick a topology", "should we use Kafka or Postgres LISTEN", "what retrieval architecture", "decide auth provider", "architecture deep research".
The run takes 3–6 minutes. You MUST stream progress to the user as events land — silent waiting is bad UX. This command uses background bash + tail -F + the Monitor tool to surface each event in chat as it happens, instead of blocking on the MCP tool until completion.
Step 1 — Confirm the decision name
Ask one question (skip if the user already named it):
What's the architecture decision? (e.g. "event bus topology", "retrieval architecture", "auth provider")
Capture as <DECISION>. Derive <SLUG> by lowercasing and replacing non-alphanum with -. Derive <DOMAIN> from the repo's README / package.json — if you can't tell, ask.
ADR produces a research report on the decision space — whatever candidates the live evidence surfaces (architecture patterns, specific products, or a mix) get their own section in research-report.json and ADR.md. The reader decides.
Step 1.5 — Ask whether to include peer products
Most architects looking at a real decision want to see 3-5 similar products and how they handle the same aspect ("what does Linear use for vector storage?" beats reading abstract benchmarks). Ask:
Question: "Should ADR also research 3-5 similar / competitor products and how each one handles
<DECISION>?"Options:
- Yes — include peers (recommended) — Discover finds 3-5 comparable products. Deep-research adds one targeted task per peer hitting their GitHub repo, docs, and engineering blog for this specific decision aspect. Adds 30-60s + a few cents to the run.
- No — skip peers — Standard pipeline only.
Capture as <INCLUDE_PEERS> (boolean). If yes, you'll pass --include-peers on the deep-research invocation below.
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.
- 2mo ago First seen · 344 lines · 54 tokens per session scan A 1f242f2e6d39
decide is a command published in the GitHub repository beevibe-ai/beevibe-cto (103 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 5,465 once invoked, about $0.0002 per session on Opus 5.5. 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.
decide compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decidebeevibe-ai/beevibe-cto | Command | 103 | 4mo ago | Apache-2.0 | A | 54 | Claude Code |
| review-branchdamusix/atomic-claude | Command | 116 | 6d ago | MIT | A | 35 | Claude Code |
| securityajitpratap0/GoSQLX | Command | 124 | today | Apache-2.0 | A | 21 | Claude Code |
| commitechoVic/blade-code | Command | 181 | 25d ago | MIT | A | 8 | Claude Code |
| modernize-transformfuxicodex/Fuxi | Command | 3.2k | 18d ago | none | A | 17 | Claude Code |
| react-nativegetsentry/toolkit | Command | 960 | today | none | A | 0 | Claude Code |
| amp-registeragentmessaging/claude-plugin | Command | 5 | 6d ago | Apache-2.0 | A | 0 | Claude Code |