draft-plan

A command that turns an active software specification into a written implementation plan. The plan lists goals, files, expected outcomes, and ways to verify each step, then waits for review before saving it.

In plain words
What is it for?
Use it to draft plans from a specification, optionally provide a task when no specification exists, and accept, edit, or reject the plan before it is written under .claude/plans/.
Why use it?
It gives a concrete, versioned plan before coding begins and ties each step to the specification’s completion criteria. This reduces the risk of implementing against an outdated or unclear specification.

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/ackeskin/contexture/draft-plan
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 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 $0.00070 $0.00250
Opus 5 $0.00035 $0.00125
Sonnet 5 $0.00014 $0.00050
Haiku 4.5 $0.00007 $0.00025

Measured 2d ago against content hash cf74ca784a14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-plan 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.

commands/draft-plan.md · 16 lines

What it actually says

Run the draft-plan skill for the current context.

Forms:

  • /draft-plan — resolve the slug from the active specs (default, sole active, or ask).
  • /draft-plan <slug> — plan against .claude/specs/<slug>/ active version.
  • /draft-plan <slug> --task "<text>" — degraded mode: no spec, the text is the input.

The skill preps architectural rules, grounds via /discover, drafts steps each tracing to the spec's done-criteria, presents the plan for accept/edit/reject (nothing written until accepted), then writes .claude/plans/<slug>/v<N>.md pinned to the spec version and reconciles INDEX.md. It does not implement or execute.

See ~/.claude/skills/draft-plan/SKILL.md for the full procedure.

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 · 16 lines · 70 tokens per session scan A cf74ca784a14

Subscribe to this mod's changes

draft-plan is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 250 once invoked, about $0.0003 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.