Instruction Reviewer — Data & AI agent for Claude Code
Reviews check-agent-docs review packets (an AI-agent instruction file plus facts check-agent-docs verified about the repo) and writes JSON answers.
How to install Instruction Reviewer
Installs to ~/.claude/agents/manishrawal95-check-agent-docs-instruction-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/manishrawal95/check-agent-docs/HEAD/agents/instruction-reviewer.md -o ~/.claude/agents/manishrawal95-check-agent-docs-instruction-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Instruction Reviewer does
name: instruction-reviewer description: Reviews check-agent-docs review packets (an AI-agent instruction file plus facts check-agent-docs verified about the repo) and writes JSON answers. Use from the check-agent-docs check skill when there are several packets to review. tools: Read, Write, Bash model: sonnet
You are the review stage of check-agent-docs. You will be given one or more packet file paths and an output file path.
- Get the review instructions by running `python3 <path to
Alternatives in Data & AI
- Svelte Correctness Review — Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for correctnes 7.2k ★
- Docs Drift Reviewer — Checks whether clickhouse-go documentation matches changes to its ClickHouse API, database/sql API, transports 3.3k ★
- Triage TS — LLM instruction for the TypeScript orchestrator triage role 93 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Principle Reviewer
sumidashi のレビューで、1つの設計思想(clean-architecture・ddd-tactical など)だけを担当して hybrid・llm のチェックを判定するサブエージェント。/sumidashi:r
Result Reviewer
Independently checks every method against the paper's reference data using the tolerances fixed in the experim
Voice Reviewer
Proactively reviews markdown content for AI writing patterns after edits. Also triggers on explicit requests t
Prose Review
Reviews prose for AI patterns, banned phrases, voice drift, and structural issues. Dispatched by the copydesk
Sync Coordinator
Use this agent to synchronize instruction files between Claude Code and GitHub Copilot platforms, plus create
Eval Inline Instruction
Eval arm inline-instruction (Q4 — the CALCULATED vs MEASURED line reduced to its INSTRUCTION half: what to out
Related Skills
House Voice
A Claude Code skill that writes marketing and sales copy in your company's real voice. It interviews you on fi
Agentic Task System
CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, prove
Audit With Verification
Run a parallel-review-then-adversarial-verify audit on a URL, feature spec, or code path. Dispatches N reviewe