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 agentmods add instructions/knowledgestack/ks-cookbook/claude-mdgit clone --depth 1 https://github.com/knowledgestack/ks-cookbookWrote 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/instructions/knowledgestack/ks-cookbook/claude-md)<a href="https://agentmods.dev/instructions/knowledgestack/ks-cookbook/claude-md"><img src="https://agentmods.dev/badge/instructions/knowledgestack/ks-cookbook/claude-md.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 | $0.01662 | $0.01662 |
| Opus 5 | $0.00831 | $0.00831 |
| Sonnet 5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
ks-cookbook 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 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Style rules (load these first)
Before editing anything, read the cursor rules that mirror ks-backend's clean-code convention:
.cursor/rules/python_clean_code.mdc— SRP, function-size limits, forbidden smells, the four prompt invariants..cursor/rules/flagship_author.mdc— file layout, README template, agent wiring, schema shape, Makefile entry, PR checklist for flagships..cursor/rules/recipe_author.mdc— ≤100-LOC cap, frontmatter, shared session helper, smoke-test bar.
What this repo is
ks-cookbook is a uv workspace of 32 flagship agent demos plus a set of lightweight recipes that sit on top of Knowledge Stack. Every flagship uses the same pattern: connect to knowledgestack-mcp (stdio), enumerate a corpus folder, read chunks, produce structured output with real [chunk:<uuid>] citations, and write a file artifact (.md / .docx / .xlsx).
The ksapi dependency resolves from PyPI (ksapi>=0.1.0). No sibling checkout of ks-backend is required. If you want to develop against the local generated SDK instead, add a [tool.uv.sources] override pointing at ../ks-backend/codegen/ks-backend-python in your own working copy — don't commit it.
Commands
All targets assume .env with KS_API_KEY + (OPENAI_API_KEY or ANTHROPIC_API_KEY).
make setup # uv sync --all-packages + check-env
make install-dev # setup + install pre-commit hooks
make lint # ruff check . (line-length 100, ignores E501/UP042)
make fix # ruff check . --fix (imports, unused, etc.)
make format # ruff format .
make test # reminder — MCP server tests live in the ks-mcp repo
make help # list every demo target
make demo-<name> # run a single flagship (e.g. demo-credit-memo)
make recipe NAME=<dir> ARGS='...' # run a recipe from recipes/<dir>/recipe.py
make clean # delete generated sample outputs from every flagship
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 · 84 lines · 1,662 tokens per session scan A d42adc312400
ks-cookbook CLAUDE.md is an instructions file published in the GitHub repository knowledgestack/ks-cookbook (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,662 tokens to every session, about $0.0083 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 instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
OpenKB AGENTS.md
AGENTS.md instructions for VectifyAI/OpenKB, covering agents.md — openkb map for coding agents, read next, dev commands, module map (openkb/) and hard invariants.
orchestkit CLAUDE.md
Claude Code instructions for yonatangross/orchestkit, covering claude.md, language, tone, visuals and project overview.
dawnai AGENTS.md
AGENTS.md instructions for cacheplane/dawnai, covering agents.md, what this is (and isn't), workspace map, definition of done and conventions.
hr-skills AGENTS.md
AGENTS.md instructions for tuanductran/hr-skills, covering hr skills development guide, project overview, branch strategy, quick start and where things live.
DocMason copilot-instructions.md
Copilot instructions for JetXu-LLM/DocMason, covering docmason github copilot notes and copilot-specific delta.