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-review-checksgit 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-review-checks)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/flows-review-checks"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-review-checks/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-review-checks"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/flows-review-checks.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.06054 |
| Opus 5 | $0.00043 | $0.03027 |
| Sonnet 5 | $0.00017 | $0.01211 |
| Haiku 4.5 | $0.00009 | $0.00605 |
Grade A, and why
flows-review-checks 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 3d 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/code-quality/SKILL.md How it starts
The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flows review checks (shared)
This file is the public definition of what a Flows technical review must search for in this repo, how strict each bar is, and how to score 1.1, 1.3–1.6, 2.1–2.6, 3.1.
It does not decide:
- whether you build the app
- Codespace vs local
- Jira / Zendesk / git round folders
- output paths (
reviews/code-review/…vsreviews/external-submissions/…)
The caller sets those. Then it reads this file and runs every check.
Do not edit the app. Do not “fix it now.”
Load code-quality from the same cognitedata/builder-skills repo (see hunt 1.5). Run its searches. Ignore every “fix / replace / write the file / pnpm add” instruction in that skill. Other skills (test-coverage, …) stay fixers and are not the review bar.
Caller contract
Before any command in this file:
cdto the app root (the directory withpackage.jsonandsrc/).- All greps and test/coverage commands run from that directory.
- The caller names where to write artifacts. This file only defines content.
If a search was not run, that check is not a pass.
What the caller must produce
Whatever the filenames, the review must include:
- File inventory — every
.ts/.tsxexceptnode_modules,dist,.cognite-bundles. Includevitest.config.*/vite.config.*/jest.config.*. Columns: Structure, Quality, Patterns, Tests, Notes. Then read every non-trivial production file (skip barrels, generated types, tests). - Findings — every hunt below, with hits or
none. Then must / should / nice withfile:line. - Package audit — Step 2 in this file.
- Scored report — criteria 1.1, 1.3–1.6, 2.1–2.6, 3.1, must/should/nice lists,
_Impact:_on every Must Fix.
A 1–2 on any criterion is Must Fix. 3 is Should Fix. Gaps at 4 are Nice Fix.
Step 1 — Hunt
Run every command. Do not sample src/ and stop.
1.1 Coverage and test config (criterion 1.4) — before you believe any %
Read vitest.config.*, vite.config.* (test / coverage blocks), and jest.config.*. Then:
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.
- 3d ago First seen · 475 lines · 86 tokens per session scan A 1ba0ca3ef853
flows-review-checks is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 86 tokens to every session and 6,054 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…