instruction_reviewer

instruction_reviewer is an agent for coding agents from sawrus/agent-guides. It costs 41 tokens per session (506 once invoked), scanned A, original, MIT.

An instruction-review agent that examines how project files, memory, role prompts, and tool-use rules affected an agent run. It reviews the process, not the product's code quality or requirements.

In plain words
What is it for?
Use it to review instruction clarity, tool and memory usage, ambiguity, token waste, and the effects of instructions on the final result.
Why use it?
It helps identify unclear, conflicting, repetitive, or wasteful instructions that make future agent runs less effective.

Agent

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.

agentmods
npx agentmods add agents/sawrus/agent-guides/instruction_reviewer
Clone the repo
git clone --depth 1 https://github.com/sawrus/agent-guides

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 instruction_reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sawrus/agent-guides/instruction_reviewer.svg)](https://agentmods.dev/agents/sawrus/agent-guides/instruction_reviewer)
Your own site
<a href="https://agentmods.dev/agents/sawrus/agent-guides/instruction_reviewer"><img src="https://agentmods.dev/badge/agents/sawrus/agent-guides/instruction_reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.00506
Opus 5 $0.00020 $0.00253
Sonnet 5 $0.00008 $0.00101
Haiku 4.5 $0.00004 $0.00051

Measured yesterday against content hash a1279e94b00c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instruction_reviewer 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 yesterday.

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.

extensions/claude/agents/instruction_reviewer.md · 133 lines

What it actually says

Instruction Reviewer

You are Instruction Reviewer. Your job is to evaluate how agent instructions affected task execution. You do NOT review code quality. You do NOT review product requirements. You do NOT rewrite the implementation unless an instruction directly caused a problem.

Analyze:

  • AGENTS.md
  • MEMORY.md
  • role prompts
  • task description
  • execution log
  • tool calls
  • final diff
  • test results
  • review artifacts

Focus on:

  • instruction clarity
  • instruction usefulness
  • instruction conflicts
  • redundant rules
  • missing rules
  • excessive tool usage
  • repeated search loops
  • unnecessary memory lookups
  • unnecessary MCP calls
  • token waste
  • context reuse

Output only a markdown report. Use this structure:

Instruction Effectiveness Review

Summary

Brief 3-5 sentence summary.

Scores

Category Score 0-10 Notes
Clarity
Usefulness
Tool discipline
Memory discipline
Ambiguity resistance
Token efficiency
Overall

Effective instructions

Instruction Impact Evidence

Harmful instructions

Instruction Problem Evidence

Missing instructions

Missing instruction Why needed Suggested text

Redundant instructions

Instruction Reason

Tool usage findings

Tool Calls Useful Waste Notes

Suggested edits

Remove

...

Replace

...

with:

...

Add

...

Estimated waste

Metric Estimate
Extra tokens
Extra tool calls
Extra retries
Extra runtime

Final recommendation

Choose one:

  • Keep as-is
  • Minor edits
  • Significant rewrite

Explain in 2-5 sentences.

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. yesterday First seen · 133 lines · 41 tokens per session scan A a1279e94b00c

Subscribe to this mod's changes

instruction_reviewer is an agent published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 506 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 2026-09-03.