work

Pick the next task grouping from a breakdown and implement it with an agent team.

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/squirrelsoft-dev/dev/work
Clone the repo
git clone --depth 1 https://github.com/squirrelsoft-dev/dev

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00015 $0.01580
Opus 5 $0.00008 $0.00790
Sonnet 5 $0.00003 $0.00316
Haiku 4.5 $0.00002 $0.00158

Measured today against content hash f02c2902b648, 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 today.

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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Next Task

Pick a task grouping from a task breakdown and spin up an agent team to implement it, guided by the specs.

Input: $ARGUMENTS — optional task list name (maps to .claude/tasks/$ARGUMENTS.md). If omitted, the user picks from available task lists.

Steps

1. Resolve the task list

  • If $ARGUMENTS is provided, read .claude/tasks/$ARGUMENTS.md. If it doesn't exist, tell the user and stop.
  • If $ARGUMENTS is not provided:
    1. Glob for all files matching .claude/tasks/*.md.
    2. For each file, read the first heading line (# Task Breakdown: ...) and check whether any tasks remain incomplete (lines matching - [ ]). Exclude files where every task is - [x].
    3. If no task lists have incomplete tasks, tell the user "All task lists are complete" and stop.
    4. Present the list to the user with AskUserQuestion — show each task list name, its heading, and a count of remaining tasks (e.g. "my-feature — 4 tasks remaining"). Let the user pick one.

2. Parse task groupings

Read the selected task list file and parse its structure:

  • Groups are headed by ## Group N — <label> lines.
  • Tasks within a group match the pattern - [ ] **Task title** (incomplete) or - [x] **Task title** (complete).
  • A group is fully complete if all its tasks are - [x].
  • A group is available if it is not fully complete and all groups it depends on (listed in the _Depends on: ..._ line) are fully complete.
  • A group is blocked if it depends on a group that still has incomplete tasks.

3. Let the user choose a task grouping

Use AskUserQuestion to present the available (non-blocked, non-complete) groups. For each group show:

  • Group number and label
  • Count of incomplete tasks in the group
  • Task titles at a glance

If only one group is available, skip the question and auto-select it.

If no groups are available (all remaining groups are blocked), tell the user which groups are blocking and stop.

4. Verify specs exist

Read the full file on GitHub · 127 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. today First seen · 127 lines · 15 tokens per session scan A f02c2902b648

Subscribe to this mod's changes

work is a command published in the GitHub repository squirrelsoft-dev/dev (14 stars, last pushed 17d ago), licensed MIT. It adds 15 tokens to every session and 1,580 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 2026-09-01.