draft

A command for proposing and preparing a new lawbook change at an agreed planning level before coding.

In plain words
What is it for?
Use it to create a feature, fix, or refactor plan, confirm its ceremony level, scaffold the needed files, and validate them.
Why use it?
It ensures the change has the right specifications and passes validation before implementation starts.

Command

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/esneiderbravo/speclaw/draft
Clone the repo
git clone --depth 1 https://github.com/esneiderbravo/speclaw
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 140 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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00140
Opus 5 $0.00007 $0.00070
Sonnet 5 $0.00003 $0.00028
Haiku 4.5 $0.00001 $0.00014

Measured yesterday against content hash 000b2214a4f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft 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.

src/modules/lawbook/assets/commands/draft.md · 12 lines

What it actually says

Draft a new change under lawbook/changes/<name>/ for: $ARGUMENTS

Follow the draft skill: ensure lawbook/ exists (lawbook_init), investigate with Compass, propose a ceremony level (lawbook_level mode propose) and confirm it with the human (set), then scaffold only the artifacts that level requires. For true one-liners use speclaw quick / the quick skill instead. Finish by running lawbook_change (action: validate) and fixing every issue.

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. yesterday First seen · 12 lines · 14 tokens per session scan A 000b2214a4f9

Subscribe to this mod's changes

draft is a command published in the GitHub repository esneiderbravo/speclaw (1 stars, last pushed 7d ago), licensed MIT. It adds 14 tokens to every session and 140 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.