work

A command for doing structured work on the c3-design project. It first identifies whether the task is a change or a troubleshooting request, then gathers project context and plans how to verify the result.

In plain words
What is it for?
Use it to improve, add, build, or troubleshoot work in c3-design, including gathering project guidance and planning tests.
Why use it?
It gives a repeatable process for understanding a request before changing code. It also makes testing and verification part of the work.

Command for Claude Code

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 commands/lagz0ne/c3-skill/work
Clone the repo
git clone --depth 1 https://github.com/lagz0ne/c3-skill

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 863 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 $0.00010 $0.00863
Opus 5 $0.00005 $0.00432
Sonnet 5 $0.00002 $0.00173
Haiku 4.5 $0.00001 $0.00086

Measured 2d ago against content hash 5c1f1a6dd92c, 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 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.

.claude/commands/work.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/work Command

Arguments

$ARGUMENTS

Intent Detection

Analyze $ARGUMENTS to determine intent:

Intent Patterns Focus
Change "improve", "add", "build", "work on", "implement", "create", "enhance" What should exist
Troubleshoot "off", "broken", "wrong", "failing", "not working", "weird", "bug" What's going wrong

Phase 1: Context Gathering (inline)

Load project understanding before launching subagents:

CLAUDE.md + references/skill-harness.md (principles)
skills/**/*.md (all skills, their connections)
git status (current state)

Summarize: What is the current state relevant to $ARGUMENTS?

Phase 2: Brainstorming (subagent)

Launch subagent with superpowers:brainstorming:

Input: Context summary + $ARGUMENTS + detected intent Goal: Pin-point the actual question/goal through socratic dialogue Output: Clear problem statement + proposed approach

If later phases find complexity, this phase may be revisited.

Phase 3: Testing Strategy (subagent)

Launch subagent to discover how to verify the work:

Input: Brainstorm output (goal + approach) Method: Socratic questioning

Questions to answer:

  • How would you know it works?
  • What's the simplest check?
  • What breaks if this is wrong?
  • What existing tests/patterns can we reuse?

Output criteria - test approach must be:

  • Fast (seconds, not minutes)
  • Good coverage (key paths)
  • Cheap to maintain (minimal fixtures)
  • Human readable (clear pass/fail)

Loop back to brainstorming if: approach is too complex to test practically

Phase 4: Writing Plans (subagent)

Launch subagent with superpowers:writing-plans:

Input: Brainstorm output + testing strategy Output: Two separate plans in docs/plans/:

  1. YYYY-MM-DD-<topic>-implementation.md - Implementation steps
  2. YYYY-MM-DD-<topic>-test.md - Test plan with verification steps

Loop back if:

  • Scope issue discovered → return to brainstorming
  • Test gap found → return to testing strategy

Read the full file on GitHub · 122 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 · 122 lines · 10 tokens per session scan A 5c1f1a6dd92c

Subscribe to this mod's changes

work is a command published in the GitHub repository lagz0ne/c3-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 863 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.