work

work is a skill for Claude Code, Codex from impactcrew/dont-be-a-sloperator. It costs 27 tokens per session (2,142 once invoked), scanned A, original, MIT.

A four-stage workflow for handling substantial tasks: understand the request, plan the work, execute it, and verify the result.

In plain words
What is it for?
Use it to structure complex coding, configuration, infrastructure, or content tasks from intake through final checks.
Why use it?
It adds checkpoints that help prevent important requirements or validation steps from being skipped.

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/impactcrew/dont-be-a-sloperator/work
Any agent
npx skills add impactcrew/dont-be-a-sloperator --skill work
Clone the repo
git clone --depth 1 https://github.com/impactcrew/dont-be-a-sloperator

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/impactcrew/dont-be-a-sloperator/work.svg)](https://agentmods.dev/skills/impactcrew/dont-be-a-sloperator/work)
Your own site
<a href="https://agentmods.dev/skills/impactcrew/dont-be-a-sloperator/work"><img src="https://agentmods.dev/badge/skills/impactcrew/dont-be-a-sloperator/work.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 2,142 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 $0.02142
Opus 5 $0.00014 $0.01071
Sonnet 5 $0.00005 $0.00428
Haiku 4.5 $0.00003 $0.00214

Measured 4d ago against content hash 54420ae445f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work 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.

skills/work/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/work - Structured Task Intake

You are starting a new task. Follow the Workflow Protocol phases strictly. Do NOT skip to output.

Iron Laws are active. Read and follow ALL Iron Laws from ~/.claude/CLAUDE.md. Tag every action with the governing law using [Law #N] inline notation. Apply the Critical Thinking checkpoint (Law #2) at every phase gate. No exceptions.

First: Determine the task type

Read the user's task description and classify:

  • Code task: Writing, modifying, or debugging code, configuration, or infrastructure
  • Content task: Writing, editing, researching, planning, or any non-code deliverable

This determines which steps apply within each phase. The four phases themselves always run in order.

Agent-first approach [Law #9] (code tasks only): For code tasks, your default mode is delegation, not serial execution. Maximum 3 concurrent agents (more kills performance). If you have more than 3 independent tasks, batch them in waves of 3. For content tasks, agents are rarely useful since the work is inherently sequential and voice/tone must stay consistent.

What the user said

The user's message after /work is the task description. If no description was provided, ask what they want to do.


Step 1: UNDERSTAND (Phase 1)

Read everything relevant before forming any opinions.

For code tasks:

Launch an Explore agent unless the affected area is fewer than 5 files that you can already identify by name:

  1. Read the project's CLAUDE.md yourself (this is fast and needed for coordination)
  2. Launch an Explore agent (subagent_type: "Explore") via the Agent tool to map the affected codebase areas
  3. If the task spans multiple distinct areas, launch separate Explore agents in parallel
  4. If you skip the Explore agent, state why: "Skipping Explore agent: affected files are [list them]."

For content tasks:

  1. Read any source material the user provided or referenced
  2. Research the topic if needed (web search, reading existing docs)
  3. Understand the context: what already exists, what this builds on, what it replaces

Read the full file on GitHub · 220 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 · 220 lines · 27 tokens per session scan A 54420ae445f3

Subscribe to this mod's changes

work is a skill published in the GitHub repository impactcrew/dont-be-a-sloperator (10 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 2,142 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens