deep-review

deep-review is a skill for Claude Code from ulises-jeremias/agent-toolkit. It costs 57 tokens per session (1,728 once invoked), scanned A, original, MIT.

A strict code-review method that records evidence-based findings about maintainability, correctness, security, performance, and testing. Each finding has a severity and a confidence level, and the review may suggest larger structural changes.

In plain words
What is it for?
Use it for deep audits, large or risky changes, shared code layers, abstraction reviews, and cases where a code-reviewer agent requests structural feedback.
Why use it?
A surface checklist can miss risky design or overly complicated code. Requiring evidence distinguishes confirmed problems from uncertain concerns and focuses attention on changes that could simplify the structure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-toolkit-complete plugin — 116 skills shipped together

Good fit Use it for deep audits, large or risky changes, shared code layers, abstraction reviews, and cases where a code-reviewer agent requests structural feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ulises-jeremias/agent-toolkit/deep-review
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.

Any agent
npx skills add ulises-jeremias/agent-toolkit --skill deep-review
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

Made for: Claude Code.

Or install agent-toolkit-complete, the plugin that ships this one along with the rest of its 116 skills.

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 deep-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/deep-review/github.svg)](https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/deep-review)
Your own site
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/deep-review"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/deep-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deep-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/deep-review"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/deep-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,728 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00057 $0.01728
Opus 5 $0.00028 $0.00864
Sonnet 5 $0.00011 $0.00346
Haiku 4.5 $0.00006 $0.00173

Measured 9d ago against content hash 60ebf4d7ec8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deep-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 9d 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.

plugins/agent-toolkit-complete/.github/skills/deep-review/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Review

A strict, evidence-cited code review rubric for when a change needs more than a surface checklist. It pushes the reviewer to be ambitious about structure — not merely to identify local cleanup, but to find "code judo" moves: restructurings that preserve behavior while making the implementation dramatically simpler, smaller, and more direct.

When to use

  • The user asks for a "deep review", "deep code quality audit", "thermo-nuclear review", "harsh maintainability review", or "review for abstraction quality".
  • A PR touches large files, shared layers, or risk-prone abstractions.
  • The code-reviewer agent flags that a change needs structural (not stylistic) feedback.

Review contract

Findings carry severity and confidence, each with an evidence citation (file:line or diff hunk) — no ungrounded opinions:

  • Severity: critical (block merge) · warning (should fix) · suggestion (consider).
  • Confidence: high (certain from the evidence) · medium (likely, needs a look) · low (hypothesis).

Baseline prompt

Perform a deep code quality audit of the current branch's changes. Rethink how to structure / implement the changes to meaningfully improve code quality without impacting behavior. Work to improve abstractions, modularity, reduce spaghetti code, improve succinctness and legibility. Be ambitious — if there is a clear path to improving the implementation that involves restructuring, pursue it. Be extremely thorough and rigorous. Measure twice, cut once.

Non-negotiable standards

  1. Be ambitious about structural simplification. Do not stop at "this could be cleaner". Look for opportunities to reframe the change so whole branches, helpers, modes, conditionals, or layers disappear. Prefer the solution that makes the code feel inevitable in hindsight. If there is a path to delete complexity rather than rearrange it, push hard for that path.

  2. Do not let a PR push a file over 1000 lines without a very strong reason. Treat this as a strong smell. Prefer extracting helpers, subcomponents, or modules. If the diff crosses the threshold, ask whether the code should be decomposed first.

Read the full file on GitHub · 149 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. 9d ago First seen · 149 lines · 57 tokens per session scan A 60ebf4d7ec8f

Subscribe to this mod's changes

deep-review is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,728 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

audit

Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…

pe-menezes/vibeflow · 93 tokens

pr-alignment-loop

Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…

nikships/skills-registry · 122 tokens

review-all

Use when the user asks for a deep review, full review, comprehensive review, production readiness assessment, full audit, multi-domain audit, "security and reliability and code review", or "review everything". Also use when the user explicitly requests performance review alongside the comprehensive request (e.g.…

paultyng/skill-issue · 102 tokens

active-review

Use when the user wants to prepare for a manual PR code review and asks for help targeting it — a terse PR summary, ranked files to read first, and paste-ready inline comment drafts with GitHub deep-links. Triggers: "active review this PR", "walk me through this PR", "help me review this", "give me inline comments to…

paultyng/skill-issue · 157 tokens

review-documentation

Review documentation quality and sync with implementation across Go doc comments, proto comments, OpenAPI specs, markdown files, and example tests. Use when the user asks for a documentation review, doc audit, or wants to check that docs are in sync with code.

paultyng/skill-issue · 55 tokens

review-api-compat

Use when the user asks for an API compatibility review, breaking change review, proto breaking change review, buf breaking review, OpenAPI compatibility check, gRPC backwards compatibility audit, "are these API changes breaking", "did we break the wire", contract evolution review, or backwards-compatibility audit on…

paultyng/skill-issue · 69 tokens