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-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/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-code-review"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Memory Poisoning · line 333 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium MCP Rug Pull · line 128 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 129 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]
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 | $0.00097 | $0.01190 |
| Opus 5.5 | $0.00039 | $0.00476 |
| Sonnet 5.5 | $0.00019 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
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 2mo 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.
curl -fsSL https://raw.githubusercontent.com/cognitedata/builder-skills/main/skills/flows-review-checks/SKILL.md How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flows Code Review
This skill is the local runner for the technical review step:
flows-app-brief → build → flows-code-review (this skill, repeat until clean) → flows-design-review → flows-external-app-submit
Checks and scoring live in flows-review-checks. Do not copy them here. Do not score from memory. Do not substitute test-coverage or other fix skills for the review bar.
This file only decides: git/app-brief pre-checks, feedback-round folder, that the working directory is the app root, where to write files, and the submitter Summary block.
Pre-checks
package.jsonexists- We are inside a git repository (
git rev-parse --git-dir) - If
App-Brief.mdis missing at repo root, warn thatflows-app-briefshould be run first, but continue
Feedback round: look at reviews/code-review/. If it doesn't exist, use feedback-round-1/. Otherwise the next missing round number.
Working directory for all review commands: repo root (the app).
Step 1 — Pull latest checks from cognitedata/builder-skills, then run them
Every review run must start by taking flows-review-checks and code-quality from cognitedata/builder-skills. Do not score from whatever is already in the app’s skills/ folder.
If this workspace already is builder-skills (git remote contains cognitedata/builder-skills): you are in that repo — Read local skills/flows-review-checks/SKILL.md (it loads local code-quality).
Otherwise (reviewing an app): pull those two skills from this repo, then read them:
npx @cognite/cli@latest apps skills pull --skill flows-review-checks
npx @cognite/cli@latest apps skills pull --skill code-quality
If the CLI pull fails, get the same two files from main:
curl -fsSL https://raw.githubusercontent.com/cognitedata/builder-skills/main/skills/flows-review-checks/SKILL.md
curl -fsSL https://raw.githubusercontent.com/cognitedata/builder-skills/main/skills/code-quality/SKILL.md
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.
- 2mo ago Changed · -304 lines · -22 tokens per session fd141fc04835
- 2mo ago Changed · +5 lines f4ad9a2651f8
- 2mo 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 97 tokens to every session and 1,190 once invoked, about $0.0004 per session on Opus 5.5. 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.
flows-code-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flows-code-reviewcognitedata/builder-skills | Skill | 6 | yesterday | Apache-2.0 | A | 97 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | 2d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |