self-review

self-review is a command for Claude Code from mims-harvard/ToolUniverse. It costs 47 tokens per session (324 once invoked), scanned A, original, Apache-2.0.

A command for reviewing current work or a supplied result against the user’s actual goal. It reports what is solid, what is missing, the main risks, and whether the work is complete.

In plain words
What is it for?
Use it to assess an answer, file, change, report, or other artifact and receive an evidence-based verdict with prioritized fixes.
Why use it?
It helps catch gaps and unsupported claims before work is treated as finished, without adding numerical grades unless the user asks for them.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the tooluniverse plugin — 140 skills, 8 commands, 1 agent, 1 hook, 1 MCP server shipped together

Good fit Use it to assess an answer, file, change, report, or other artifact and receive an evidence-based verdict with prioritized fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mims-harvard/tooluniverse/self-review
About the project

ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.

mims-harvard/ToolUniverse · 1,676 stars · on GitHub · aiscientist.tools

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.

Clone the repo
git clone --depth 1 https://github.com/mims-harvard/ToolUniverse

Made for: Claude Code.

Or install tooluniverse, the plugin that ships this one along with the rest of its 140 skills, 8 commands, 1 agent, 1 hook, 1 MCP server.

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 self-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/self-review.svg)](https://agentmods.dev/commands/mims-harvard/tooluniverse/self-review)
Your own site
<a href="https://agentmods.dev/commands/mims-harvard/tooluniverse/self-review"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/self-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 324 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 $0.00047 $0.00324
Opus 5 $0.00023 $0.00162
Sonnet 5 $0.00009 $0.00065
Haiku 4.5 $0.00005 $0.00032

Measured 8d ago against content hash 58c512667621, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

self-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 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.

plugin/commands/self-review.md · 29 lines

What it actually says

Apply the tooluniverse-self-review skill to this request: $ARGUMENTS

Interpret the request

  • Treat $ARGUMENTS as the evaluation instruction and optional target, not automatically as the task being evaluated.
  • If $ARGUMENTS is empty or refers to "current work", "this", or "what we have", recover the original goal and current work from the conversation and available artifacts.
  • If an artifact, answer, file, diff, or section is supplied explicitly, review that target against its stated or preceding goal.
  • Plain eval, evaluate, review, assess, or check requests are qualitative. Do not generate points, grades, weighted criteria, or numeric totals unless $ARGUMENTS explicitly asks for them.
  • If the request is to create an eval suite, test, grader, or benchmark, treat it as an engineering task rather than running self-review.

Produce

By default, give a concise evidence-backed assessment with findings ordered by impact, meaningful strengths, prioritized fixes, and a plain-language completion verdict. Do not print RET scenarios, perspectives, criteria tables, or scoring machinery unless explicitly requested.

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 · 29 lines · 47 tokens per session scan A 58c512667621

Subscribe to this mod's changes

self-review is a command published in the GitHub repository mims-harvard/ToolUniverse (1,676 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 324 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 2026-08-30.