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.
npx agentmods add skills/cognitedata/builder-skills/flows-code-reviewnpx skills add cognitedata/builder-skills --skill flows-code-reviewgit clone --depth 1 https://github.com/cognitedata/builder-skillsWrote 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.
[](https://agentmods.dev/skills/cognitedata/builder-skills/flows-code-review)<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>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.
| Model | Per session | Once 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 |
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. 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.jsonexists (Node/TS project)- We are inside a git repository (
git rev-parse --git-dir) - If
App-Brief.mdis missing at repo root, warn the user thatflows-app-briefshould 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 importsconnectToHostApp,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.
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.
- 2d ago Changed · +5 lines f4ad9a2651f8
- 6d ago First seen · 411 lines · 119 tokens per session scan A 821436cbf2a0
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…