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 skills/everywan-dev/claude-code-engineering/choose-the-right-code-reviewnpx skills add everywan-dev/claude-code-engineering --skill choose-the-right-code-reviewgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWrote 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/skills/everywan-dev/claude-code-engineering/choose-the-right-code-review)<a href="https://agentmods.dev/skills/everywan-dev/claude-code-engineering/choose-the-right-code-review"><img src="https://agentmods.dev/badge/skills/everywan-dev/claude-code-engineering/choose-the-right-code-review.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.01790 |
| Opus 5 | $0.00020 | $0.00895 |
| Sonnet 5 | $0.00008 | $0.00358 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
choose-the-right-code-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 3d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choose the right code review
How much review a change needs is not a judgement made in the moment by the person who wrote it. It is decided by what the change touches, before the change is written, by a table.
The reason is simple: the author is the worst-placed person in the building to estimate the risk of their own change. Everything they thought of is already handled. The risk lives entirely in what they did not think of.
When to use this
- A change is finished and you are about to ask for review
- You are deciding whether "this is tiny, just merge it" is true
- You are assembling reviewers and need to know how many and which
- A change has grown since it started and may have crossed a line
The routing table
| Level | The change touches | Reviews | One of them must |
|---|---|---|---|
| 1 | Cosmetic, documentation, anything that never reaches production | 1 | Look at the rendered result, not the source |
| 2 | Code in production, service configuration, build pipelines, dependencies | 2, independent | Judge whether the evidence could have failed |
| 3 | Authentication, permissions, money, customer data, schema migrations, deletions, network and firewall rules, certificates, anything that runs everywhere at once | 3, independent | Actively try to break it |
Classifying without debate
If the change touches any of these, it is level 3. No discussion, no weighing:
- login, passwords, tokens, sessions, permissions, roles
- amounts, prices, refunds, balances, invoicing
- customer or personal data
- schema changes, deletions, table drops, bulk updates
- network rules, firewall, address translation, routing
- certificates and their renewal
- anything applied to every site, tenant or node in one action
Touches production but none of the above → level 2. Never reaches production → level 1.
⚠️ The size of the diff does not appear anywhere in this table. A one-line change to a permission check is level 3. A two-thousand-line documentation rewrite is level 1.
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.
- 3d ago First seen · 177 lines · 41 tokens per session scan A 9c9258f11440
choose-the-right-code-review is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,790 once invoked, about $0.0002 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 skills, from other repositories
claude-project-manifest
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
proofpress
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
PBE Extractor
Extract invariant principles from any text — find the ideas that survive rephrasing.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.
book-to-skill
Use when convert technical books and documents (PDF, EPUB, DOCX, HTML, Markdown, RTF, MOBI) into structured agent skills with frameworks, mental models, chapter references, and decision rules. Includes full extraction pipeline. Use when the user wants to turn a book or document collection into a reusable agent skill…