sw-plan

sw-plan is a skill for Claude Code, Codex from Obsidian-Owl/specwright. It costs 27 tokens per session (2,418 once invoked), scanned A, original, MIT.

A planning tool that turns an approved software design into detailed work specifications and ordered tasks. It can split larger work into separate units, each with implementation plans and testable acceptance criteria.

In plain words
What is it for?
Use it to prepare implementation-ready plans for a feature or larger project, break multi-part work into units, and define checks that show when each unit is complete.
Why use it?
It removes the gap between agreeing on a design and knowing exactly what to build and how to check it. It also keeps supporting decisions, project rules, and technical documents connected to the plan.

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/obsidian-owl/specwright/sw-plan
Any agent
npx skills add Obsidian-Owl/specwright --skill sw-plan
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sw-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-plan.svg)](https://agentmods.dev/skills/obsidian-owl/specwright/sw-plan)
Your own site
<a href="https://agentmods.dev/skills/obsidian-owl/specwright/sw-plan"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/sw-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,418 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 $0.00027 $0.02418
Opus 5 $0.00014 $0.01209
Sonnet 5 $0.00005 $0.00484
Haiku 4.5 $0.00003 $0.00242

Measured 5d ago against content hash f223bc9e41cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sw-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 5d 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.

core/skills/sw-plan/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specwright Plan

Goal

Turn the approved design into implementation-ready specs with testable acceptance criteria. Decompose into ordered work units if large. Operates autonomously, applying protocols/decision.md for all decisions. Gate handoff at the end.

Inputs

  • {worktreeStateRoot}/session.json -- selected work for this worktree
  • {repoStateRoot}/work/{selectedWork.id}/workflow.json -- selected work state
  • {workArtifactsRoot}/{selectedWork.id}/design.md -- approved solution design
  • {workArtifactsRoot}/{selectedWork.id}/context.md -- research findings from sw-design
  • {workArtifactsRoot}/{selectedWork.id}/decisions.md -- design-phase decisions
  • Conditional design artifacts: data-model.md, contracts.md, testing-strategy.md, infra.md, migrations.md
  • {projectArtifactsRoot}/CONSTITUTION.md -- practices to follow
  • {projectArtifactsRoot}/config.json -- project configuration

Outputs

Single-unit work: spec.md + plan.md in {workArtifactsRoot}/{selectedWork.id}/ (flat layout).

Multi-unit work: For each unit in {workArtifactsRoot}/{selectedWork.id}/units/{unit-id}/: spec.md + plan.md + context.md. workUnits array in workflow.json. Also: integration-criteria.md in the design-level directory ({workArtifactsRoot}/{selectedWork.id}/).

Also: {repoStateRoot}/work/{selectedWork.id}/stage-report.md for the planning handoff.

Also: decisions.md updated with planning-phase autonomous decisions.

Constraints

Stage boundary (LOW freedom): Follow protocols/stage-boundary.md. Produce specs and plans. NEVER implement, branch, test, or commit. After gate handoff, STOP.

Pre-condition check (LOW freedom): Resolve the selected work from the current worktree session. Check that selectedWork.status is designing or planning and design.md exists. sw-plan operates on the current worktree's attached work only. If another live top-level worktree owns that selected work, STOP and require explicit /sw-adopt guidance before mutating specs or plans here. Matching the recorded branch alone must not imply takeover.

Read the full file on GitHub · 193 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. 5d ago First seen · 193 lines · 27 tokens per session scan A f223bc9e41cf

Subscribe to this mod's changes

sw-plan is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 2,418 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.

Related

Other skills, from other repositories

rust-skills

Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.

martineserios/thebrana · 23 tokens

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

shinpr/claude-code-workflows · 52 tokens

cco-task

Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.

egorfedorov/claude-context-optimizer · 70 tokens

cco-templates

Manage context templates for common task types.

egorfedorov/claude-context-optimizer · 11 tokens

discuss

Use when exploring a feature idea before committing, or revisiting a parked one. Triggers — "/engineer.discuss", "/engineer.discuss ", "I have an idea about", "should we build", "let's think about".

swingerman/engineer · 54 tokens