cook CLAUDE.md

Project instructions for a Claude Code plugin called juni, which combines structured feature-development workflows with a safety guide for JSON data. It uses project context, routing policies, and operational rules.

In plain words
What is it for?
Use them when developing features with juni or handling JSON data through its cook and guard workflows.
Why use it?
They help the agent follow the project's workflow and safety rules instead of relying only on informal prompts.

Instructions file

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.

agentmods
npx agentmods add instructions/pjuniszewski/cook/claude-md
Clone the repo
git clone --depth 1 https://github.com/PJuniszewski/cook
Per session 1,616 This file is loaded in full into every session.
When invoked 1,616 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01616 $0.01616
Opus 5 $0.00808 $0.00808
Sonnet 5 $0.00323 $0.00323
Haiku 4.5 $0.00162 $0.00162

Measured 2d ago against content hash c9a9566205c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cook CLAUDE.md 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 2d 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.

CLAUDE.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

juni Plugin Project Rules

Purpose

This repo contains the juni plugin - a Claude Code plugin suite combining:

  • /juni:cook - Structured feature development workflows
  • /juni:guard - Epistemic safety for JSON data

Architecture: Multi-Layer Context System

Cook uses a layered approach combining narrative context with operational contracts and explicit policies:

┌─────────────────────────────────────────────────────────┐
│ CLAUDE.md / AGENTS.md (Narrative Layer)                 │
│ "What we build, why, how we work"                       │
│ → Global project context, loaded in Phase 0             │
└─────────────────────────────────────────────────────────┘
                         ↓
┌─────────────────────────────────────────────────────────┐
│ ROUTER_POLICY.md (Router/Policy Layer)                  │
│ "Who decides when"                                      │
│ → Phase routing, escalation paths, conflict resolution  │
└─────────────────────────────────────────────────────────┘
                         ↓
┌─────────────────────────────────────────────────────────┐
│ .claude/agents/*_chef.md (Operational Layer)            │
│ non_negotiables, escalation, rubric, output_contract    │
│ → Per-phase contracts, loaded before each step          │
└─────────────────────────────────────────────────────────┘
                         ↓
┌─────────────────────────────────────────────────────────┐
│ CHEF_CONTRACTS.md (Handoff Layer)                       │
│ "What is passed to whom"                                │
│ → Input/output contracts, handoff validation            │
└─────────────────────────────────────────────────────────┘
                         ↓
┌─────────────────────────────────────────────────────────┐
│ FALLBACK_POLICY.md (Fallback Layer)                     │
│ "What when we can't decide"                             │
│ → Recovery paths, timeouts, degradation modes           │
└─────────────────────────────────────────────────────────┘
                         ↓
┌─────────────────────────────────────────────────────────┐
│ .claude/data/cook-audit.jsonl (Audit/Memory Layer)      │
│ "What did we learn"                                     │
│ → Event logging, pattern analysis, improvements         │
└─────────────────────────────────────────────────────────┘

Read the full file on GitHub · 175 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. 2d ago First seen · 175 lines · 1,616 tokens per session scan A c9a9566205c8

Subscribe to this mod's changes

cook CLAUDE.md is an instructions file published in the GitHub repository PJuniszewski/cook (13 stars, last pushed 6mo ago), licensed MIT. It adds 1,616 tokens to every session, about $0.0081 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 instructions, from other repositories