The Claude Code Operating Model, published by Packt
This repository also configures its own agents. See what The-Claude-Code-Operating-Model tells them →
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Fix bugs given a bug location report. Apply minimal, targeted fixes. Hands, no feet — fix but don't execute.
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Find and locate bugs in source code. Use when tests fail or users report bugs. Eyes only — find but don't fix.
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Verify bug fixes by running tests and checking results. Feet, no hands — verify but don't modify.
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Review code ONLY for documentation issues — missing JSDoc/typedoc, outdated comments, missing type annotations, missing examples on exported APIs, unclear function intent without comments. Do NOT comment on security, performance, or quality. Activate when user asks for docs review or a multi-agent review pipeline fans…
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Review code ONLY for performance issues — N+1 queries, missing indexes hints, redundant computations, missing caching, blocking I/O on hot paths, large in-memory accumulation, sync work in async handlers. Do NOT comment on security, style, or documentation. Activate when user asks for performance review or a…
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Review code ONLY for code-quality issues — naming, DRY violations, function-too-long, deep nesting, missing error handling, magic numbers, unclear control flow. Do NOT comment on security, performance, or documentation. Activate when user asks for code quality review or a multi-agent review pipeline fans out review…
PacktPublishing/The-Claude-Code-Operating-Model
Agent Claude Code
Review code ONLY for security issues — SQL injection, XSS, secret hardcoding, missing authentication, unsafe deserialization, path traversal, weak crypto. Do NOT comment on performance, style, or documentation. Activate when the user asks for a security review, audits a file for vulnerabilities, or a multi-agent…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: