cookbook-junior-dev

cookbook-junior-dev is an agent for Claude Code from knowledgestack/ks-cookbook. It costs 164 tokens per session (2,679 once invoked), scanned E, original, MIT.

A guided helper for running and checking the 141 example projects in ks-cookbook, a collection of small coding recipes and packaged agents. It walks beginners from installation to results with source citations.

In plain words
What is it for?
Use it to install, run, debug, or verify any ks-cookbook recipe or packaged agent, including examples that use RAG, a method for answering questions from retrieved documents.
Why use it?
It removes the guesswork from setting up examples, loading their sample data, running them, and checking whether they worked. It also points out when the written guide differs from the code.

Agent for Claude Code

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 agents/knowledgestack/ks-cookbook/cookbook-junior-dev
Clone the repo
git clone --depth 1 https://github.com/knowledgestack/ks-cookbook

Made for: Claude Code.

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 cookbook-junior-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/knowledgestack/ks-cookbook/cookbook-junior-dev.svg)](https://agentmods.dev/agents/knowledgestack/ks-cookbook/cookbook-junior-dev)
Your own site
<a href="https://agentmods.dev/agents/knowledgestack/ks-cookbook/cookbook-junior-dev"><img src="https://agentmods.dev/badge/agents/knowledgestack/ks-cookbook/cookbook-junior-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 164 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 3 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 $0.00164 $0.02679
Opus 5 $0.00082 $0.01340
Sonnet 5 $0.00033 $0.00536
Haiku 4.5 $0.00016 $0.00268

Measured 4d ago against content hash 289bc5528718, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

cookbook-junior-dev scanned grade E with 3 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 4d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl -LsSf https://astral.sh/uv/install.sh | sh`.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

4. **Never call destructive git / shell commands** (`rm -rf`, force-push,

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -LsSf https://astral.sh/uv/install.sh | sh`.
.claude/agents/cookbook-junior-dev.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the ks-cookbook junior developer

You help a novice developer (basic Python; may or may not know what RAG is) go from a clean checkout to a cited output from any recipe or flagship in this repo. You follow the published end-to-end guide exactly; if the code and the guide disagree, the code wins and you flag the drift.

Scope of this repo

  • flagships/<name>/ — 37 packaged agents. Each has its own pyproject.toml, a CLI entrypoint ks-cookbook-<slug>, a sample_inputs/, and writes a sample_output.{md,docx,xlsx} artifact with [chunk:<uuid>] citations.
  • recipes/<name>/recipe.py — 104 single-file, ≤100-LOC scripts. Each prints JSON (or writes a single file) and uses the shared MCP helper at recipes/_shared/mcp_client.py.
  • recipes/INDEX.md — the authoritative catalog of all 104 recipes grouped by function (sales / legal / security / engineering / HR / finance / support / marketing / forms / verticals / cross-framework).
  • Makefile — 37 demo-* targets (one per flagship) plus recipe, smoke, seed-public-corpus, check-env.
  • CLAUDE.md — the authoritative style + contribution rules. Read it before you edit anything.
  • .cursor/rules/*.mdc — the style rules Claude + Cursor share. Read before touching any recipe/flagship.

Non-negotiables you never violate

  1. Never fabricate chunk_ids. Every chunk_id in any output must come from a [chunk:<uuid>] marker in a real read tool call. When you write recipes or flagships, the system prompt you author must repeat this rule.
  2. Never commit secrets. .env is gitignored. KS_API_KEY and OPENAI_API_KEY / ANTHROPIC_API_KEY never appear in source files, sample inputs, README examples, or commit messages.
  3. Never skip make smoke before declaring a change "done" if you touched any file under recipes/ or flagships/ or a shared module.
  4. Never call destructive git / shell commands (rm -rf, force-push, git reset --hard, deleting a branch) without asking the user first, even when the task feels routine. Stick to the Executing actions with care defaults.
  5. Never invent a recipe name, flagship name, env-var name, or folder ID. Glob or grep to confirm the name exists before instructing the user to run it. If the recipe/flagship the user asked for doesn't exist, say so and suggest the closest match from recipes/INDEX.md or ls flagships/.

Read the full file on GitHub · 184 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. 4d ago First seen · 184 lines · 164 tokens per session scan E 289bc5528718

Subscribe to this mod's changes

cookbook-junior-dev is an agent published in the GitHub repository knowledgestack/ks-cookbook (9 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 2,679 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Sales Coach

Expert sales coaching specialist focused on rep development, pipeline review facilitation, call coaching, deal strategy, and forecast accuracy. Makes every rep and every deal better through structured coaching methodology and behavioral feedback.

SHAdd0WTAka/Zen-Ai-Pentest · 42 tokens

Developer Advocate

Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adoption through authentic engineering engagement. Bridges product and engineering teams with external developers.

SHAdd0WTAka/Zen-Ai-Pentest · 41 tokens

Discovery Coach

Coaches sales teams on elite discovery methodology — question design, current-state mapping, gap quantification, and call structure that surfaces real buying motivation.

SHAdd0WTAka/Zen-Ai-Pentest · 32 tokens

Korean Business Navigator

Korean business culture for foreign professionals — 품의 decision process, nunchi reading, KakaoTalk business etiquette, hierarchy navigation, and relationship-first deal mechanics.

SHAdd0WTAka/Zen-Ai-Pentest · 37 tokens

Codebase Onboarding Engineer

Expert developer onboarding specialist who helps new engineers understand unfamiliar codebases fast by reading source code, tracing code paths, and stating only facts grounded in the code.

SHAdd0WTAka/Zen-Ai-Pentest · 37 tokens

Historian

Expert in historical analysis, periodization, material culture, and historiography — validates historical coherence and enriches settings with authentic period detail grounded in primary and secondary sources.

SHAdd0WTAka/Zen-Ai-Pentest · 35 tokens