A setup command that creates Casebook files in a project: a work board and a case-study document. A case study is a written record of what happened, why decisions were made, and what was learned.

Use it at the beginning of a project to provide the project name, your role, and whether the Casebook files should be committed to version control or ignored.

It provides a structured starting point for tracking work and preserving the project story. It also checks for an existing `.casebook/` folder before making changes.

init — Command by vldesigns

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 commands/vldesigns/casebook/init

Clone the repo

git clone --depth 1 https://github.com/vldesigns/casebook

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 503 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00014	$0.00503
Opus 5	$0.00007	$0.00251
Sonnet 5	$0.00003	$0.00101
Haiku 4.5	$0.00001	$0.00050

Measured yesterday against content hash 8fa2cfb7021b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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.

commands/init.md · 43 lines

What it actually says

Set up Casebook in the current project.

Step 1: Preflight.

If .casebook/ already exists in the project root, STOP and ask before touching anything — never overwrite an existing board or case study.
Confirm you can locate the project root (git rev-parse --show-toplevel; fall back to the current directory and note that git-linked features like commit evidence will be limited).

Step 2: Ask the user three setup questions (one message, all three):

Project name (for the case study title).
Their role in one line (e.g. "Design founder — owning the product end to end"). This seeds the case study's TL;DR table.
Should .casebook/ be committed to the repo, or gitignored? Recommend committed — the case study travels with the project. Suggest gitignored for client work or private notes.

Step 3: Scaffold.

Run: "$CLAUDE_PLUGIN_ROOT/scripts/tracker" focus "First session — set up Casebook" (this creates .casebook/state.json with defaults).
Copy $CLAUDE_PLUGIN_ROOT/templates/case-study.md to .casebook/case-study.md, replacing {{PROJECT}} with the project name, {{ROLE}} with the role, and {{START_DATE}} with today's date (e.g. "July 2026").
If the user chose gitignored: append .casebook/ to the project's .gitignore (create it if missing).

Step 4: Orient the user. Briefly explain the loop:

/casebook:check-work at session start reads the board and proposes what to pick up.
Work happens; the board can be updated any time via the tracker CLI.
/casebook:end-work at session close syncs the board against actual commits and offers a dated Running Log entry for the case study.
"$CLAUDE_PLUGIN_ROOT/scripts/tracker" prompt --copy produces a kickoff prompt for starting a fresh AI session with full board context.

Then suggest adding their first cards, e.g.: "$CLAUDE_PLUGIN_ROOT/scripts/tracker" add upnext "First real task" --notes "..."

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.

yesterday First seen · 43 lines · 14 tokens per session scan A 8fa2cfb7021b

Subscribe to this mod's changes

init is a command published in the GitHub repository vldesigns/casebook (1 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 503 once invoked, about $0.0001 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.

Documents Project management case study claude-code claude-code-plugin design-engineering kanban

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

flux-generate

flux-add

card

OPSX: Propose

build-docs

wisp-dashboard