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 skills add cognitedata/builder-skills --skill flows-app-briefgit 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-app-brief)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/flows-app-brief"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-app-brief/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.
<a href="https://agentmods.dev/skills/cognitedata/builder-skills/flows-app-brief"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-app-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 7 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 29 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 34 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00104 | $0.02900 |
| Opus 5 | $0.00052 | $0.01450 |
| Sonnet 5 | $0.00021 | $0.00580 |
| Haiku 4.5 | $0.00010 | $0.00290 |
Grade A, and why
flows-app-brief 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flows App Brief (Certification Coach)
This is step 1 of the Flows app certification flow:
flows-app-brief (this skill) → build → flows-code-review → flows-design-review → flows-external-app-submit
Your job is to act as a certification coach for Cognite Builders: ask focused questions, challenge vague answers, and produce a complete App-Brief.md at the workspace root.
Preflight — Refresh review skills
Before doing anything else, ask (via AskQuestion):
"Pull the latest review skills before we start?"
- Pull —
npx @cognite/cli@latest apps skills pull- Skip — use what's already in
.agents/skills//.claude/skills/
On Pull:
- Run
Bash npx @cognite/cli@latest apps skills pull. Glob '**/skills/correctness-and-error-handling/SKILL.md'as a sentinel.- Match found → continue.
- Zero matches → ask: "Skills pull didn't succeed — Retry / Skip and continue (review quality may degrade) / Stop."
On Skip: continue immediately.
Operating rules
- Coaching from scratch is one question at a time. When you have no pre-scanned draft for a coached field and must elicit the answer fresh, use a single-question
AskQuestioncall. Keep your prose short between questions. - Confirming pre-scanned drafts can be batched. When Step 0 produced strong drafts (e.g. from
specs/<NNN>/spec.md), it is fine and encouraged to present them in a singleAskQuestioncall with three options each: (a) accept the draft, (b) accept a clearly-labeled refined variant, (c) "I'll write my own". This is the fast path and should be the default when drafts exist. - When the user gives a confident, specific answer, save it immediately and move on. Restate the captured answer in one sentence so the user can see what you stored.
- When an answer is vague, challenge it before saving using the rubric below. Re-ask until specific.
- Never invent answers on the user's behalf. If the user explicitly says they do not know, capture that as an honest assumption (the field allows this).
- If
App-Brief.mdalready exists at the workspace root, parse its YAML frontmatter, show the current values, and only re-coach the fields the user wants to revise.
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.
- 11d ago First seen · 227 lines · 104 tokens per session scan A 8ae7f2964051
flows-app-brief is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,900 once invoked, about $0.0005 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.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…