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.
npx agentmods add commands/stefan-jansen/claude-code-toolkit/workgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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.
| Model | Per session | Once 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 |
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.
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
- Find target unit (last active or specified ID)
- Load metadata and state from
.claude/work/{id}/ - Set as ACTIVE_WORK
- Display current task and next steps
Checkpoint
- Verify active work unit exists
- Create checkpoint in
{work_unit}/checkpoints/ - Record timestamp, message, and current state
Switch
- Auto-checkpoint current work (if any)
- Validate target work unit exists
- Set new unit as ACTIVE_WORK
- 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
/explorecreates new work units/plangenerates state.json/nextexecutes tasks/shipcompletes and archives
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.
- 2d ago First seen · 74 lines · 11 tokens per session scan A 0b5163ff70b4
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.
Other commands, from other repositories
remember
Save something to agent memory - picks project or user scope automatically from context.
disambiguate-plan
Thorough collaborative planning with iterative disambiguation - resolves all ambiguity before planning.
pr-review
Review a GitHub pull request: analyzes changed files to select relevant reviewers, loads project and user memory, runs reviewers in parallel, lets the user pick which findings to post, then submits the review on behalf of the user via gh CLI.
dataviz
Define chart types, color encoding, and data display conventions.
ship
Pre-launch gate — six-domain checklist before any production deployment.
build
Implement the next ready task from .forge/tasks.yaml using TDD discipline.