code-review

An independent review process for checking a code change against its specification, decisions, tasks, tests, maintainability, scope, and rollback needs.

In plain words
What is it for?
Use it before committing, deploying, or merging a change, or when reviewing a concrete diff for safety and consistency with the project requirements.
Why use it?
It identifies issues that could block a commit, deployment, or merge without changing the code itself.

Skill for Claude CodeCodex

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 skills/fusebase-dev/fusebase-flow/code-review
Any agent
npx skills add fusebase-dev/fusebase-flow --skill code-review
Clone the repo
git clone --depth 1 https://github.com/fusebase-dev/fusebase-flow

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,066 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 $0.00055 $0.03066
Opus 5 $0.00028 $0.01533
Sonnet 5 $0.00011 $0.00613
Haiku 4.5 $0.00006 $0.00307

Measured yesterday against content hash 998a5d1e2981, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 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.

.agents/skills/code-review/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Purpose

Independent review of a diff against the spec contract, locked decisions, and FLOW_RULES — before commit, deploy, or merge. Distinguishes blockers (must fix) from non-blockers (should fix).

When to invoke

  • Operator says "review this" / "is this safe to ship?" / "look at the diff"
  • AI Developer-session gate report has been pasted and validation-and-qa ran clean — code-review is the next step before deploy
  • About to merge a PR (team mode)
  • Major refactor in flight and operator wants midpoint review

Do not invoke when

  • No diff exists yet (review needs concrete code)
  • Clarifications are unresolved or scope is not yet locked — review against an incomplete contract is noise
  • Operator wants the code fixed — review surfaces issues; fixes go through implementation

Required inputs

Input Where it lives If missing
Diff git diff <baseline>..HEAD or PR diff URL Stop; ask which diff to review
Spec docs/specs/<slug>/spec.md Stop; review without spec is style-only and limited
Decisions docs/specs/<slug>/decisions.md Stop; cannot verify decision adherence
Tasks docs/specs/<slug>/tasks.md Stop; cannot verify scope adherence
CLI edition map, for Fusebase Apps work docs/fusebase-cli-edition.md Continue with Flow-only review, but mark app-domain review criteria unknown

Procedure

  1. Trust the recorded gate verdict (review boundary). When validation-and-qa has recorded a gate verdict ("Gate verified. Phase advances to Deploy."), trust it for the deterministic/cross-artifact fields — AC↔task map, decisions-cited-in-tasks, lint/typecheck status, TODO/FIXME/WIP scan, protected-path diff. Do not re-verify them; carry the gate's AC↔task verdict into the review's spec-alignment matrix by citation. If no gate verdict exists, route to validation-and-qa first — do not absorb its checks here.
  2. Run git diff <baseline>..HEAD --stat to get changed files. For Fusebase Apps diffs, read docs/fusebase-cli-edition.md and load the relevant CLI provider skills as review standards for app/runtime/domain behavior.
  3. Semantic review per task T: read the corresponding commit (or accumulated diff). Judge:
    • Scope-creep: does the change match the intent of the tasks.md description, not just touch the listed files?
    • Decision adherence in meaning: the gate checks decisions are cited; review checks the code does what the locked decision means (cite letter+number on divergence)
    • Quality-pattern ACs (QP-xx, flow-skills/app-quality-patterns): the cited pattern's Requirement is actually met by the implementation (semantic, by reading — e.g., is the filter state really in the URL, does the delete really handle children)
  4. Maintainability scan:
    • Type safety (no broad casts on external JSON, no any)
    • Comment policy (FR-22) — see the dedicated dimension in step 4b
    • Function size and complexity reasonable

Read the full file on GitHub · 165 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. yesterday First seen · 165 lines · 55 tokens per session scan A 998a5d1e2981

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 3,066 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 2026-08-31.

Related

Other skills, from other repositories

adobe-express-core

Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.

Sandgrouse/adobe-express-dev-skill · 50 tokens

adobe-express-monetization

Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.

Sandgrouse/adobe-express-dev-skill · 44 tokens

adobe-express-spectrum-ui-ux

Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…

Sandgrouse/adobe-express-dev-skill · 70 tokens

adobe-express-cors-and-backend

Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…

Sandgrouse/adobe-express-dev-skill · 92 tokens

adobe-express-document-manipulation

Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.

Sandgrouse/adobe-express-dev-skill · 43 tokens

adobe-express-oauth-authentication

Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.

Sandgrouse/adobe-express-dev-skill · 50 tokens