work

A command for managing named work units, which are saved pieces of development work with their own progress and context. It can list, resume, checkpoint, or switch between them.

In plain words
What is it for?
Use it to review active work, continue a previous task, save a progress checkpoint, or change to another work unit.
Why use it?
It prevents progress and task context from being lost when moving between tasks or pausing work.

Command

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/stefan-jansen/claude-code-toolkit/work
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00011 $0.00524
Opus 5 $0.00005 $0.00262
Sonnet 5 $0.00002 $0.00105
Haiku 4.5 $0.00001 $0.00052

Measured 2d ago against content hash 0b5163ff70b4, 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.

plugins/workflow/commands/work.md · 74 lines

What it actually says

Work Management

Manage work units: list status, continue work, save checkpoints, switch contexts.

Input: $ARGUMENTS

Commands

Command Description
/work List all work units
/work active List only active units
/work continue Resume last active unit
/work continue ID Resume specific unit
/work checkpoint Save current progress
/work checkpoint "msg" Save with message
/work switch ID Switch to different unit

List Display

📋 WORK UNITS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🟢 2025-01-01_01_auth    [implementing]  3/5 tasks (60%)
⏸️  2025-01-01_02_api     [paused]        1/4 tasks (25%)
✅ 2024-12-31_01_setup   [completed]     4/4 tasks (100%)

Operations

Continue

  1. Find target unit (last active or specified ID)
  2. Load metadata and state from .claude/work/{id}/
  3. Set as ACTIVE_WORK
  4. Display current task and next steps

Checkpoint

  1. Verify active work unit exists
  2. Create checkpoint in {work_unit}/checkpoints/
  3. Record timestamp, message, and current state

Switch

  1. Auto-checkpoint current work (if any)
  2. Validate target work unit exists
  3. Set new unit as ACTIVE_WORK
  4. Load new context

Work Unit Location

.claude/work/
├── ACTIVE_WORK              # Current unit ID
├── 2025-01-01_01_topic/
│   ├── metadata.json        # Status, timestamps
│   ├── requirements.md
│   ├── state.json           # Task tracking
│   └── checkpoints/
└── 2025-01-01_02_other/

Integration

  • /explore creates new work units
  • /plan generates state.json
  • /next executes tasks
  • /ship completes and archives
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 · 74 lines · 11 tokens per session scan A 0b5163ff70b4

Subscribe to this mod's changes

work is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 524 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.