claude-orchestrator-server: Skill for Claude Code

.claude/skills/code-review-guidelines/SKILL.md

code-review-guidelines is a skill for Claude Code from adamancyzhang/claude-orchestrator-server. It costs 39 tokens per session (1,341 once invoked), scanned A, original, MIT.

A general code-review standard for checking whether code tests real behavior, reports configuration errors clearly, and is structured so its logic can be tested. A fallback is an alternate behavior used when something expected is missing.

In plain words
What is it for?
Use it when reviewing code changes, evaluating test quality, checking error handling, or deciding whether a refactor makes important logic easier to verify.
Why use it?
It helps reviewers detect tests that pass without exercising production code and errors that are hidden by silent defaults or meaningless fallbacks.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is adamancyzhang/claude-orchestrator-server's own configuration. It tells Claude Code how to work on claude-orchestrator-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-orchestrator-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adamancyzhang/claude-orchestrator-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adamancyzhang/claude-orchestrator-server/master/.claude/skills/code-review-guidelines/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-server

Made for: Claude Code.

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.

agentmods badge for code-review-guidelines

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/code-review-guidelines.svg)](https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/code-review-guidelines)
Your own site
<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/code-review-guidelines"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/code-review-guidelines.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,341 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.01341
Opus 5 $0.00019 $0.00671
Sonnet 5 $0.00008 $0.00268
Haiku 4.5 $0.00004 $0.00134

Measured 8d ago against content hash ffceb3750a5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-review-guidelines 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 8d 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.

.claude/skills/code-review-guidelines/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Guidelines

Overview

Review code for structural robustness, error sensitivity, and test authenticity. A passing test that exercises copied logic proves nothing. A system that silently degrades on missing configuration is broken in ways no test will catch.

Core principle: If a configuration error does not crash, you do not know it happened.

When to Use

Always:

  • Reviewing any code change before commit
  • Assessing test quality and coverage
  • Evaluating error-handling patterns
  • Refactoring decisions

No exceptions. Every code change that reaches review must pass this standard.

The Iron Law

NO SILENT FALLBACK FOR MISSING CONFIGURATION

Missing template, missing required file, missing required parameter — throw immediately. Do not substitute a default. Do not skip the step. Do not log a warning and continue.

No exceptions:

  • Not for "better user experience"
  • Not for "the system should be resilient"
  • Not for "it's unlikely to happen"

Resilience means handling runtime failures gracefully. It does not mean hiding configuration errors.

Test Real Code

Unit tests must exercise production code paths. If logic cannot be tested through its public API, the code structure needs refactoring — extract pure functions, inject dependencies, split modules — before writing the test.

Copying logic into tests creates drift. The copied code and the production code diverge silently. The test passes while the production code is broken. A passing copy-paste test is worse than no test — it creates false confidence.

Mock only external boundaries: process spawning, network calls, filesystem. Internal logic must never be replaced by mocks in tests.

Structural Decomposition for Testability

Test difficulty is a signal. When code is hard to test, the problem is the code structure, not the test approach. More mocks, deeper stubs, or wider integration tests are not the answer.

Extract the untestable logic into a pure function with explicit inputs and outputs. Inject the dependency through the constructor or function parameter. Let the test pass real values and assert real results.

Read the full file on GitHub · 132 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.

  1. 8d ago First seen · 132 lines · 39 tokens per session scan A ffceb3750a5d

Subscribe to this mod's changes

code-review-guidelines is a skill published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,341 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.

Related

Other skills, from other repositories