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/review)<a href="https://agentmods.dev/commands/beevibe-ai/beevibe-cto/review"><img src="https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/review/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/review"><img src="https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/review.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 | $0.00071 | $0.01128 |
| Opus 5 | $0.00036 | $0.00564 |
| Sonnet 5 | $0.00014 | $0.00226 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
review 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/adr:review — Dynamic PR review against team principles
Use when the user wants the bot to PR-review a change against the team's own conventions, not generic style rules. Requires /adr:principles to have run at least once.
Step 0 — Check principles exist
If .adr/principles.json doesn't exist in the repo, tell the user:
Your team principles haven't been discovered yet. Run
/adr:principlesfirst — it scans the repo and learns what your team's conventions are, so PR review can cite your own code.
Stop. Do not proceed.
Step 1 — Figure out what to review
If the user typed /adr:review 42, that's PR #42. Otherwise ask one short question:
What do you want me to review?
- A PR — give me the number
- Your staged changes (
git diff --staged)- Your current branch vs main
Skip the question if the user already said.
Step 2 — Detect violations via the MCP server
Call adr_review with the appropriate source:
{ "pr_number": 42 }
or
{ "staged": true }
or
{ "branch": "main" }
The tool returns structured violations (each with principle_id, file, line, severity, message, suggested_fix) and the matching principles array (id, rule, rationale, examples_to_follow).
Runs in 30-90 seconds depending on diff size. Costs $0.01-$0.05 on gpt-4.1-mini.
Step 3 — If no violations: ship it
If violation_count is 0:
No principle violations in this change. Ship it.
Stop.
Step 4 — Walk through violations one at a time
For each violation in the returned list:
-
Show the user this block:
[N/total] <SEVERITY-COLORED> file.ts:LINE Team principle: <principle.rule> <principle.rationale> Why this hunk fails: <violation.message> Team example to follow: <principle.examples_to_follow[0]> Fix: <violation.suggested_fix> -
Ask one short question:
Post / edit / skip?
-
Capture the answer. If "edit", let them rewrite the comment text. Track which violations get accepted.
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 · 137 lines · 71 tokens per session scan A 5ae3d8d5366d
review is a command published in the GitHub repository beevibe-ai/beevibe-cto (106 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,128 once invoked, about $0.0004 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
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
sync-pr-body
Bring the pull request description back in line with the code after correction rounds changed it. The description was written when the draft PR opened; corrections since then may have falsified specific claims in it. Your product is an accurate PR body — nothing else.
hatch3r-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.
done
Finish a task - document, create PR or merge, close.
release
Release project using adaptive learned configuration.
worktree
Worktree lifecycle management - create, list, remove, info on interactive worktrees.