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.
git clone --depth 1 https://github.com/oalders/kitchen-sinkWrote 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/commands/oalders/kitchen-sink/code-review-intense-flow)<a href="https://agentmods.dev/commands/oalders/kitchen-sink/code-review-intense-flow"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/code-review-intense-flow.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 | $0.00034 | $0.02895 |
| Opus 5 | $0.00017 | $0.01448 |
| Sonnet 5 | $0.00007 | $0.00579 |
| Haiku 4.5 | $0.00003 | $0.00290 |
Grade A, and why
code-review-intense-flow 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 6d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Intense Flow
Overview
Fan-out orchestrator that dispatches all relevant specialized reviewers in parallel for a single diff, then aggregates the findings. This is the heavyweight counterpart to /code-review-flow — use it when you want every applicable lens applied (security, frontend, SEO, GEO, Playwright, design-handoff, agent-instructions) instead of only the general reviewer.
The general-purpose reviewer always runs. Specialists fire only when the diff touches their domain, with one exception: /security-review runs by default unless the diff is documentation-only.
When to Use
Use when:
- About to open or merge a PR with non-trivial changes
- Branch touches multiple concerns (UI + routes + content)
- Coming back to a long-running branch and want a thorough sweep
- Want the e2e-coverage check for newly added routes
Don't use when:
- Quick sanity check during local iteration — use
/code-review-flowinstead - Diff is doc-only AND you want zero ceremony — use
/code-review-flowor skip review
Steps
1. Get Git SHAs
Check conversation context first. If not available, run as separate Bash calls (not chained) to avoid permission prompts:
git merge-base origin/main HEAD
git rev-parse HEAD
2. Inspect the Diff
git diff --name-only BASE_SHA..HEAD_SHA
git diff --stat BASE_SHA..HEAD_SHA
Record the list of changed files. You'll use it for routing.
3. Apply Routing Rules
| Reviewer | Fires when |
|---|---|
| General-purpose reviewer | Always |
/security-review |
Default. Skip only if doc-only (every changed file matches *.md, *.txt, docs/**, CHANGELOG*, LICENSE*, README*, .github/**/*.md AND no code files were touched) |
/frontend-review |
Diff touches *.jsx, *.tsx, *.vue, *.svelte, *.html, *.css, *.scss, or known frontend paths (components/, pages/, app/, views/, templates/) |
/design-handoff-review |
Diff touches UI files (*.css, *.scss, *.js, *.ts, *.jsx, *.tsx, *.html, *.vue, *.svelte, or a templates/ path) AND the repo contains a design-handoff bundle |
/seo-review |
Diff touches page templates, route definitions, <head>/meta tags, sitemap.*, robots.txt, canonical URL config, Open Graph / Twitter Card tags |
/geo-review |
Diff touches content pages, llms.txt, llms-full.txt, JSON-LD schema, AI-bot rules in robots.txt, author bios, About page |
/playwright-review |
Test files touched (*.spec.*, *.test.* under e2e/, tests/e2e/, playwright/) OR new route added without a corresponding test (see route detection below) OR new/changed client-side interactive behavior without an e2e test exercising it — even when no new server route was added (see interaction detection below) |
/agent-instructions-review |
Diff touches CLAUDE.md, AGENTS.md, .cursor/rules/**, .cursorrules, .github/copilot-instructions.md, or .claude/**/*.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.
- 6d ago First seen · 211 lines · 34 tokens per session scan A 63fe906c7372
code-review-intense-flow is a command published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 2,895 once invoked, about $0.0002 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 commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.