spec-draft

An interactive drafting workflow that turns an idea and its source notes into four committed specification files: requirements, design, tasks, and test plans. A specification describes what software should do and how the work will be checked.

In plain words
What is it for?
Use it to gather requirements, examine notes and transcripts, detect overlap with existing specifications, and create a draft specification on its own Git branch.
Why use it?
It gives vague ideas a documented structure while keeping the specification in draft form until a person reviews and approves it.

Skill for Claude CodeCodex

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 skills/inkatze/planwright/spec-draft
Any agent
npx skills add inkatze/planwright --skill spec-draft
Clone the repo
git clone --depth 1 https://github.com/inkatze/planwright

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,295 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 $0.00099 $0.06295
Opus 5 $0.00049 $0.03148
Sonnet 5 $0.00020 $0.01259
Haiku 4.5 $0.00010 $0.00630

Measured 2d ago against content hash a9c990094685, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-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 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.

skills/spec-draft/SKILL.md · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-draft

The authoring entry point of the planwright pipeline (REQ-B1.1): a Socratic, interactive elicitation that turns an idea plus its seed material into a compliant four-file bundle at specs/<spec>/, Status Draft, committed on the spec branch. Drafting ends where comprehension begins: /spec-kickoff walks the Draft to sign-off and flips it Ready. This skill never pushes, never opens a PR, and never flips a status to Ready — sign-off is a reserved human control it has no business near.

Doctrine

Resolve and read the run-start rule docs via the rule-doc resolution convention (scripts/resolve-rule-doc.sh <doc-name> or the documented PLANWRIGHT_ROOT/CLAUDE_PLUGIN_ROOT chain): interaction-style (governs every exchange in the flow), research-rigor (REQ-D1.5 wires its triggers into drafting), security-posture (artifact data-hygiene for everything committed), and proportionality. Four more are read point-of-use, at the step that applies them: the elicitation reads spec-format at its start (the meta-spec the bundle must conform to — its structural conventions govern every phase's output and the Completion bundle write; the gists the earlier steps need are stated inline — the extend-mode terminal-state refusal at Pre-flight, the append/supersede discipline at Extend mode — so only the full law defers, and no bundle write happens before the load); the design phase reads engineering-decisions (governs design-phase recommendations) and customization-boundary (the capability-vs-style scoping call the design phase applies when a candidate feature looks like a packaged preference — see Design step 3); the altitude gate reads autopilot-reflex (D-11 wires its altitude gate into drafting the same way research-rigor is wired — the seed-claim and mid-flow trigger classes, the phase re-anchor, and the trigger-scoped altitude record; the trigger summaries the earlier steps need are stated inline at Seed gathering and the phase re-anchor in Elicitation, so only the full law defers; this skill cites doctrine/autopilot-reflex.md rather than restating it). Their definitions govern wherever this skill names a concept. If one of those does not resolve — at run start or at its point of use — halt with a clear message naming the missing doc and the chain consulted (REQ-K1.7: a clear message is the graceful arm; proceeding without doctrine is the opaque failure). Also resolve decision-domains (the design phase walks its catalog) — this one degrades instead of halting: if absent, the design phase notes the missing catalog in one line and proceeds (the builder/catalog wiring is a hook point, not a dependency).

Read the full file on GitHub · 421 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. 2d ago First seen · 421 lines · 99 tokens per session scan A a9c990094685

Subscribe to this mod's changes

spec-draft is a skill published in the GitHub repository inkatze/planwright (3 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 6,295 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

seeds-issue-audit

Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".

jayminwest/warren · 67 tokens

good-first-issue-batch

File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…

jayminwest/warren · 80 tokens

os-eco-dep-sync

Bump warren onto the latest published @os-eco/ versions across package.json + bun.lock and the Dockerfile CLI pins, then run the gates and open a PR. Use when checking if warren is on the newest burrow/plot/canopy/seeds/mulch/sapling.

jayminwest/warren · 69 tokens

release

Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.

jayminwest/warren · 39 tokens

create-coordclaw-team

A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.

CoordClaw/CoordClaw · 42 tokens

write-file

Replaces OpenClaw built-in write tool for all plain text writing, providing.

CoordClaw/CoordClaw · 618 tokens