flows-code-review

flows-code-review is a skill for Claude Code from cognitedata/builder-skills. It costs 119 tokens per session (5,160 once invoked), scanned A, original, Apache-2.0.

A technical review process for Cognite Flows apps that checks source files, packages, correctness, security, dependencies, and tests, then records a scored report.

In plain words
What is it for?
Use it to perform the code-review stage of Flows app certification and produce review files and a report.
Why use it?
It gives a repeatable way to find implementation problems before an app moves through certification. The findings are grouped by how urgently they need attention.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/cognitedata/builder-skills/flows-code-review
Any agent
npx skills add cognitedata/builder-skills --skill flows-code-review
Clone the repo
git clone --depth 1 https://github.com/cognitedata/builder-skills

Made for: Claude Code.

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 flows-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-code-review.svg)](https://agentmods.dev/skills/cognitedata/builder-skills/flows-code-review)
Your own site
<a href="https://agentmods.dev/skills/cognitedata/builder-skills/flows-code-review"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00119 $0.05160
Opus 5 $0.00060 $0.02580
Sonnet 5 $0.00024 $0.01032
Haiku 4.5 $0.00012 $0.00516

Measured 2d ago against content hash f4ad9a2651f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

flows-code-review scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. Verify that no `gh api` calls or `curl` to `raw.githubusercontent.com` were made during this skill run — all guidance should have come from local skill reads (Step 1) and the inlined rubric above.
skills/flows-code-review/SKILL.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flows Code Review

This skill is the technical review step of the Flows app certification flow:

flows-app-brief  →  build  →  flows-code-review (this skill, repeat until clean)  →  flows-design-review  →  flows-external-app-submit

Pre-checks

Before starting, confirm:

  • package.json exists (Node/TS project)
  • We are inside a git repository (git rev-parse --git-dir)
  • If App-Brief.md is missing at repo root, warn the user that flows-app-brief should be run first, but continue.

Determine the feedback round: look at reviews/code-review/. If it doesn't exist, use feedback-round-1/. Otherwise increment to the next missing round number.

Step 1 — Load review guidance

Before any scoring, read all relevant skill files. The skills ship alongside this skill in the same repo and are available locally. For each skill below, Glob '**/skills/<name>/SKILL.md' and Read the first match.

Required reads (always):

Skill Informs criteria
correctness-and-error-handling 1.1 (bugs), 1.4 (tests), plus error-state patterns
security 1.2 (CDF via SDK), 1.3 (dependencies, CVEs)
dependencies-audit 1.3 (packages audit)
test-coverage 1.4 (coverage gate), 1.6 (testability)
code-quality 1.5 (dead code), 1.6 (patterns)
dm-limits-and-best-practices 2.1–2.5 (DMS query patterns, limits, rate)
performance 2.3–2.4 (pagination, call rate)
design 3.1 (Aura consistency)

Conditional read:

  • setup-flows-auth — read if the app imports connectToHostApp, useHostApp, or configures OAuth in Vite.
  • integrate-fusion-agent — if the app has chat, Atlas, an agent, or LLM calls. Custom in-app chat is Should Fix; uncapped completions over query results are Must Fix.

Note on DMS patterns: the dm-limits-and-best-practices skill is the canonical local reference for search vs joins, cardinality, and query-time semantics — no external semantic-knowledge/ submodule is needed.

Read the full file on GitHub · 416 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. 2d ago Changed · +5 lines f4ad9a2651f8
  2. 6d ago First seen · 411 lines · 119 tokens per session scan A 821436cbf2a0

Subscribe to this mod's changes

flows-code-review is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 5,160 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens