sw-do

sw-do is a skill for Claude Code from anton-abyzov/specweave. It costs 41 tokens per session (1,288 once invoked), scanned A, original, MIT.

A task-by-task implementation workflow for SpecWeave increments, which are documented units of work with a specification, acceptance criteria, and task list. It records evidence for each completed task and verifies the final close.

In plain words
What is it for?
Use it to choose the next available task, claim its files, read the applicable requirements, implement the change, run proof checks, and close the increment.
Why use it?
It keeps implementation tied to the agreed requirements and prevents agents from editing files before claiming the relevant task. It also leaves a test result or commit reference for completed work.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

Good fit Use it to choose the next available task, claim its files, read the applicable requirements, implement the change, run proof checks, and close the increment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anton-abyzov/specweave/sw-do
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.

Any agent
npx skills add anton-abyzov/specweave --skill sw-do
Clone the repo
git clone --depth 1 https://github.com/anton-abyzov/specweave

Made for: Claude Code.

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-do

README.md
[![agentmods](https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-do/github.svg)](https://agentmods.dev/skills/anton-abyzov/specweave/sw-do)
Your own site
<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-do"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-do/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sw-do

Your own site · 80×15
<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-do"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-do.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00041 $0.01288
Opus 5 $0.00020 $0.00644
Sonnet 5 $0.00008 $0.00258
Haiku 4.5 $0.00004 $0.00129

Measured 5d ago against content hash 8588907f8122, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sw-do 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.

skills/sw-do/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sw-do — work an increment to done

One loop: pick a task, claim it, implement inside its Files:, prove it with a test, record the evidence. Repeat until nothing is claimable, then verify and close. State is the ledger (sw-task); the spec is the contract.

Run specweave --version: exit 0 → CLI path. Not found → manual path (same files, appended by hand — see sw-task).

Pick the increment

No id given → the single increment whose metadata.json has status: active. Several active → list them and ask which. None → run sw-increment first.

The loop

  1. Nextspecweave task next <inc>: the first open task whose deps are done and whose Files: no live claim holds. Manual: lowest open T-id in tasks.md with no live claim in ledger.jsonl.
  2. Claimspecweave task claim T-01 <inc> (exit 3 = someone owns it, pick another · 4 = Files overlap · 6 = deps unmet). Manual: append {"t":"T-01","e":"claim","by":"<agent>","at":"<ISO>"}. Never edit before claiming.
  3. Read — the task's AC: ids in spec.md and its Files:. Read the Approach section for that scope only; do not re-read the whole repo.
  4. Implement — inside that task's Files: and nothing else. Need another file → claim the task that owns it, or add a task: ### T-07 Title + - AC: AC-03 | Files: src/b.ts | Test: npm test -- b.
  5. Prove — run the task's Test: command. Red → fix; never continue past a failing test.
  6. Commit — subject starts with the increment id: git commit -m "0042: fold the ledger".
  7. Done with evidencespecweave task done T-01 <inc> --run "npm test -- a" (exit 5 = the command failed, task stays open). No Test:--evidence "<sha> + what you ran". Manual: append {"t":"T-01","e":"done","by":"<agent>","at":"<ISO>","evidence":"npm test -- a → exit 0 / <sha>"}.
  8. Stuck / not neededtask block T-01 --note "<what is missing>" or task skip T-01 --note "<why>" (skip is terminal and needs a reason).
  9. Back to 1.

Read the full file on GitHub · 79 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 · 79 lines · 41 tokens per session scan A 8588907f8122

Subscribe to this mod's changes

sw-do is a skill published in the GitHub repository anton-abyzov/specweave (160 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,288 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

clickup

Use when managing ClickUp tasks, sprints, or comments via the cup CLI tool. Triggers: task queries, status updates, sprint tracking, creating subtasks, posting comments, threaded replies, standup summaries, searching tasks, checking overdue items, assigning tasks, listing spaces and lists, opening tasks in browser…

krodak/clickup-cli · 125 tokens

linear-graphql-skill

Operate Linear workspace issues, projects, and teams through Linear GraphQL API using UXC. Use when tasks require querying or creating issues, managing projects, or interacting with Linear workflow. Supports both Personal API Key and OAuth authentication.

holon-run/uxc · 51 tokens

genie-orca-wish

Turn a brainstorm/design into an APPROVED-able wish whose Dispatch plan is the literal input to Orca tasks and Linear issues. High-reasoning pass: pre-decide everything so fast workers can execute without judgment calls.

automagik-dev/genie · 51 tokens

dos-dispatch

Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.

anthony-chaudhary/dos-kernel · 56 tokens

dos-next-up

Snapshot the repo's phased-plan portfolio into a dispatch packet: audit candidates with dos verify, render who-does-what, and emit a dos gate verdict. Use when you need the current next-work view before dispatching agents.

anthony-chaudhary/dos-kernel · 53 tokens

aigon-next

Suggest the most likely next workflow action based on current context.

jayvee/aigon · 15 tokens