work-step

work-step is a skill for Claude Code, Codex from jakubsuplicki/codument. It costs 21 tokens per session (1,954 once invoked), scanned A, original, Apache-2.0.

A project skill for carrying out the next approved step in a documented delivery plan. It uses the project’s planning and context files to identify the correct work.

In plain words
What is it for?
It helps select the first unfinished plan step, load the relevant context, update progress checklists, implement the step, and run the required workflow commands.
Why use it?
It reduces guesswork about what to implement next and keeps changes tied to an approved plan and the project’s documented rules.

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/jakubsuplicki/codument/work-step
Any agent
npx skills add jakubsuplicki/codument --skill work-step
Clone the repo
git clone --depth 1 https://github.com/jakubsuplicki/codument

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 work-step

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakubsuplicki/codument/work-step.svg)](https://agentmods.dev/skills/jakubsuplicki/codument/work-step)
Your own site
<a href="https://agentmods.dev/skills/jakubsuplicki/codument/work-step"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/work-step.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,954 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 $0.00021 $0.01954
Opus 5 $0.00010 $0.00977
Sonnet 5 $0.00004 $0.00391
Haiku 4.5 $0.00002 $0.00195

Measured 4d ago against content hash 960a02ae29a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-step 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 4d 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.

.agents/skills/work-step/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Step

Use this when the user says to continue, work the next step, or implement the approved plan.

Workflow

  1. Find the active plan in the relevant docs/features/*.md or docs/concepts/*.md.
  2. Confirm the plan status is approved.
  3. Pick the first unchecked delivery-plan step.
  4. Surface the checklist in the live view (see Plan Checklist Mirror below): mirror the plan's steps into your host's native to-do panel with the step you are about to implement marked in progress, and run codument steps --emit so codument watch shows the active step. Post that checklist inline in the chat as well — the step just completed, the step now starting, and what remains — because the native to-do panel and the watch tape are not the chat transcript, and a run that does not wait between steps otherwise advances with no in-chat marker.
  5. Read docs/.registry.json before touching source files — codument context --plan <active-plan> pulls the grounded working set for every feature the plan routes to (owning docs, invariants with their test pointers, primary sources, one-hop deps) in one deterministic command, and --feature <slug> / --file <path> narrows it to the slice this step touches. When the question is only which doc owns this file — the one fact you need before editing it — --file <path> --owner answers in a line instead of a pack, so the lookup is cheap enough to actually run rather than guess. Fall back to reading the registry directly if the CLI is unavailable.
  6. Implement only that step.
  7. Use tdd or the strongest practical verification loop.
  8. Register each NEW source file by running codument map materialize <file> (see Feature Map Materialization), then update the mapped docs + registry as part of the same step.
  9. Mark the step complete — in the plan doc, and in the mirrored native to-do list — only after verification passes. If this was the final step, compact the ## Delivery Plan block per plan-with-docs (Compaction on ship): lift surviving decisions into ## Decisions/ADRs and any newly-true constraint into ## Invariants & boundaries, then delete the delivery scaffolding so the durable doc is left in the standard's layers.
  10. Proceed directly to review-work for this step without waiting. Never start the next delivery-plan step from here — review and commit come first, in either mode.
  11. In gated mode, stop instead and present the user with end-of-step options:
    • Run review-work now (recommended)
    • Make a specific correction to this step
    • Pause here

Read the full file on GitHub · 73 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. 4d ago First seen · 73 lines · 21 tokens per session scan A 960a02ae29a9

Subscribe to this mod's changes

work-step is a skill published in the GitHub repository jakubsuplicki/codument (47 stars, last pushed 13d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,954 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 2026-08-30.

Related

Other skills, from other repositories

vibe-workflow

Complete 5-step workflow to build an MVP from idea to launch. Use when the user wants to start a new project from scratch, go through the full workflow, or says "help me build an MVP", "start new project", or "vibe coding workflow".

KhazP/vibe-coding-prompt-template · 59 tokens

project-butler

Project memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organization, document archiving, language switching, versioned update logs, rule review, status, wiki sync, and context recovery. Use for /project-butler, setup/初始化, foundation setup, profile setup, end session/收工…

JamesShi96/project-butler · 133 tokens

implement

Implement an approved plan. Write code, tests, and docs following the sprint checklist in NEXT-TASKS.md.

cortex-tms/cortex-tms · 25 tokens

submit

Complete submission workflow - quality checks, commit, PR creation, changelog generation, and final push. Use after finishing implementation work.

lablup/backend.ai · 28 tokens

trellis-workflow-enhancer

Audit and apply real, project-local Trellis integrations for Matt Pocock and Waza skills, with phase routing, hook injection, durable artifact handoffs, and smoke-test evidence. Use when a user wants to strengthen, compare, modernize, integrate, or debug Trellis with Matt/Waza workflows, especially when skills are…

lei1024/trellis-workflow-enhancer · 79 tokens

import

Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.

skullninja/coco-workflow · 26 tokens