A tool that studies a repository to discover the team's code-review principles, such as preferred patterns and practices to avoid. It records those principles with references to the relevant files and lines.

Use it to create the principles file that the review command needs before checking pull requests or local changes against team conventions.

It gives later reviews a picture of how this team actually builds software instead of applying rules chosen from outside the repository.

principles — Command for Claude Code by beevibe-ai/beevibe-cto

Install

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.

Clone the repo

git clone --depth 1 https://github.com/beevibe-ai/beevibe-cto

Made for: Claude Code.

Or install adr, the plugin that ships this one along with the rest of its 6 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/principles/github.svg)](https://agentmods.dev/commands/beevibe-ai/beevibe-cto/principles)

Your own site

<a href="https://agentmods.dev/commands/beevibe-ai/beevibe-cto/principles"><img src="https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/principles/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/beevibe-ai/beevibe-cto/principles"><img src="https://agentmods.dev/badge/commands/beevibe-ai/beevibe-cto/principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,277 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00092	$0.01277
Opus 5.5	$0.00037	$0.00511
Sonnet 5.5	$0.00018	$0.00255
Haiku 4.5	$0.00009	$0.00128

Measured 2mo ago against content hash 073c284dc1e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

principles 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.

plugin/commands/principles.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/adr:principles — Discover the team's code-review principles

Use when the user wants the bot to learn their team's conventions so PR review can cite the team's own code as the reference.

Step 1 — Check the environment

npx -y --package=github:beevibe-ai/beevibe-cto adr-doctor

adr principles only needs an LLM provider (no web search). If that one is missing, invoke /adr:doctor.

Step 2 — Set expectations, then run

Before calling the tool, tell the user EXACTLY what's about to happen — the tool runs for 2-4 minutes with no other visible output, so without this the user just sees a spinner.

Print something like:

Running principles discovery on the repo. This takes ~2-4 minutes and runs in five steps:

Scan the repo (files, manifests, docs) — instant

Sample ~24 representative source files — instant

Extract product intent + discover review lenses (parallel LLM, ~15s)

Per-lens pattern extraction (parallel LLM, ~30s)

Consolidate + cite-verify + write .adr/principles.{md,json} (~30s)

Cost: ~$0.15 on gpt-4.1-mini. You'll see the result when it's done.

THEN call the adr_principles MCP tool with non_interactive: true:

{
  "repo_path": ".",
  "non_interactive": true
}

The MCP server emits notifications/message for every step, and notifications/progress when the client opts in via _meta.progressToken. Some clients surface these in the spinner; others don't. Either way the upfront step list gives the user something to read.

The tool returns the lenses, the per-lens patterns, AND the product intent block (identity, architectural_intent, product_philosophy, non_goals). The full content lives in .adr/principles.{md,json} on disk.

Step 3 — Show the user what we found

Read .adr/principles.json to see the full structure. Then show the user — lead with the product portrait, NOT the lint rules:

What this is — the identity field. One sentence on what the product actually is.
Architectural intent — the 3-6 foundational decisions from architectural_intent. Each with its why and the files cited.
Product philosophy — the 3-6 recurring design principles from product_philosophy. These are the team's voice — quote verbatim where pulled from CLAUDE.md / AGENTS.md.
Non-goals — what the team explicitly chose NOT to do. Often the most telling part.
Code-level lenses + their principles — show top 2-3 strongest per lens, with team file:line citations.

Read the full file on GitHub · 94 lines

Changes

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 · 94 lines · 92 tokens per session scan A 073c284dc1e7

Subscribe to this mod's changes

principles is a command published in the GitHub repository beevibe-ai/beevibe-cto (103 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,277 once invoked, about $0.0004 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.

Code review agent-skills ai ai-agents cli cto deep-research

principles next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
principlesbeevibe-ai/beevibe-cto	Command	103	4mo ago	Apache-2.0	A	92	Claude Code
review-branchdamusix/atomic-claude	Command	116	6d ago	MIT	A	35	Claude Code
reviewGoldziher/ai-rulez	Command	167	yesterday	MIT	A	11	Claude Code
anchorsraccioly/docguard	Command	32	3d ago	MIT	A	11	Claude Code
advanced-code-review-contextaxiomantic/spellbook	Command	11	4d ago	MIT	A	19	Claude Code
code-review-giveaxiomantic/spellbook	Command	11	4d ago	MIT	A	17	Claude Code
mach12:issue-reviewLeanAndMean/scramjet	Command	8	5d ago	Apache-2.0	A	17	Claude Code