eat-the-broccoli

eat-the-broccoli is a skill for Claude Code from EmpiricaAI/empirica. It costs 136 tokens per session (6,816 once invoked), scanned A, original, MIT.

A structured quality sweep for software before a release, after a refactor, or when something seems wrong. It combines automated checks with a manual search for failures that tests may miss, such as races, stale caches, and silent fallbacks.

In plain words
What is it for?
Use it for linting, fast or full tests, dependency vulnerability checks, dead-code checks, silent-failure checks, contract reviews, and manual pattern hunts.
Why use it?
It checks both known tool-detectable problems and subtle behavior that can pass tests while still breaking in production. You can limit the review to changed code, a module, or the whole repository.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the empirica plugin — 17 skills, 2 commands, 4 agents shipped together

Good fit Use it for linting, fast or full tests, dependency vulnerability checks, dead-code checks, silent-failure checks, contract reviews, and manual pattern hunts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/empiricaai/empirica/eat-the-broccoli
Install

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.

Any agent
npx skills add EmpiricaAI/empirica --skill eat-the-broccoli
Clone the repo
git clone --depth 1 https://github.com/EmpiricaAI/empirica

Made for: Claude Code.

Or install empirica, the plugin that ships this one along with the rest of its 17 skills, 2 commands, 4 agents.

Wrote 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.

agentmods badge for eat-the-broccoli

README.md
[![agentmods](https://agentmods.dev/badge/skills/empiricaai/empirica/eat-the-broccoli/github.svg)](https://agentmods.dev/skills/empiricaai/empirica/eat-the-broccoli)
Your own site
<a href="https://agentmods.dev/skills/empiricaai/empirica/eat-the-broccoli"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/eat-the-broccoli/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.

agentmods 80×15 button for eat-the-broccoli

Your own site · 80×15
<a href="https://agentmods.dev/skills/empiricaai/empirica/eat-the-broccoli"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/eat-the-broccoli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, 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 Excessive Agency · line 129
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.06816
Opus 5 $0.00068 $0.03408
Sonnet 5 $0.00027 $0.01363
Haiku 4.5 $0.00014 $0.00682

Measured 13d ago against content hash 12ecec866888, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

eat-the-broccoli 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 13d 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.

empirica/plugins/claude-code-integration/skills/eat-the-broccoli/SKILL.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eat the Broccoli 🥦

The thorough quality sweep you run before a release, after a refactor, or when something just smells off. Two halves:

  1. Deterministic tooling — lint, types, tests, dependency CVEs, dead code, silent failures. Catches the known categories.
  2. The pattern hunt — a checklist of the hard failure classes that pass every test and still ship broken: races, stale caches, silent fallbacks, null-masking, deploy-staleness. Tools can't catch these; only a trained eye plus a "is this by design?" check can.

Portable by design. The deterministic half is tool-agnostic — wire in your stack's linter / typechecker / scanner. The pattern hunt needs no tooling at all; it's a structured way of looking.


Two dials: depth × scope

Depth digs into Scope covers
quick lint + fast tests + dep-audit changed the diff vs your base branch
standard + dead-code, silent-failure, contract guards, pattern hunt module one subsystem / path
deep + full pattern hunt, docs/contract accuracy, multi-pass repo everything

Pick any combination — quick × changed is a pre-commit reflex; deep × repo is a pre-release gate. State the level + scope you chose, and say what you skipped — silent truncation reads as "covered everything."

Forks & monorepos: when most of the tree is upstream/vendored, repo scope drowns in code you don't own. Default to changed or your owned packages — here the scope dial is load-bearing, not optional.

Read the full file on GitHub · 270 lines

Changes

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.

  1. 13d ago First seen · 270 lines · 136 tokens per session scan A 12ecec866888

Subscribe to this mod's changes

eat-the-broccoli is a skill published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 6,816 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

workflow-builder

Design, build, and maintain autonomous OpenClaw workflows (stewards). Use when creating new workflow agents, improving existing ones, evaluating automation opportunities, or debugging workflow reliability. Triggers on "build a workflow", "create a steward", "automate this process", "workflow audit", "what should I…

TechNickAI/openclaw-config · 86 tokens

smart-delegation

Intelligent task delegation — route to think with deep reasoning for hard problems, or Grok for unfiltered takes. Teaches when to escalate, how to pack context into sub-agent spawns, and how to communicate delays transparently. Default: handle directly on chat (thinking off). Escalate only when the quality gain…

TechNickAI/openclaw-config · 80 tokens

review

A pause before an artifact goes into the world. Reviews external comms, money, calendar, public posts, or send-as-operator actions through a small panel of independent lenses (empathy first) and returns a verdict of pass / edit / hold / block.

TechNickAI/openclaw-config · 55 tokens

claude-code

Route real repo work to Claude Code instead of editing by hand. Triggers on "claude code" or "cc", and on any request to edit, fix, refactor, or open a PR in a repo outside /.openclaw/workspace. Claude Code picks up the repo's CLAUDE.md / AGENTS.md, applies its standards, and knows the /ai-coding-config:multi-review…

TechNickAI/openclaw-config · 105 tokens

cortex

Personal knowledge compiler and memory system. Ingests raw sources (documents, notes, transcripts, captures) into a structured, interlinked knowledge base. Maintains living entity pages, learning analysis, and the MEMORY.md routing table. Replaces the librarian skill.

TechNickAI/openclaw-config · 55 tokens

drive-to-done

Drive a task all the way to a verified done state — write DoD first, verify each item with evidence, stop only at named stop conditions.

TechNickAI/openclaw-config · 35 tokens