do-task

A task-running command for projects that track development work in a TASKS.md file and follow the Vsync project rules. It uses a test-first workflow when implementing tasks.

In plain words
What is it for?
Use it to start a named phase task, pick the next unfinished task, inspect the current phase, and implement work from TASKS.md.
Why use it?
It keeps task selection and implementation tied to the project's documented phase, rules, configuration, and specifications. This reduces the chance of working on the wrong task or skipping required project checks.

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/nicepkg/vsync/do-task
Clone the repo
git clone --depth 1 https://github.com/nicepkg/vsync

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 2,777 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 $0.02777
Opus 5 $0.00005 $0.01388
Sonnet 5 $0.00002 $0.00555
Haiku 4.5 $0.00001 $0.00278

Measured 2d ago against content hash b9b88e62afc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-task 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/do-task.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Do Task - vsync

Execute development tasks from TASKS.md following vsync project specifications and TDD workflow.

Current Context

  • Current branch: !git branch --show-current
  • Git status: !git status --short | head -20

Phase Overview

!grep -E "^## Phase [0-9]:|^\*\*Current Status\*\*:" TASKS.md | head -20

Instructions

1. Task Selection

If $ARGUMENTS is provided:

  • If it's a phase-task reference (e.g., Phase 1.1, Phase 2.3), work on that specific task
  • If it's next, pick the next uncompleted task [ ] in the current phase

If no argument, show current phase and ask which task to work on.

2. Before Starting - CRITICAL READS

MUST READ in this order:

Document Purpose Time Critical Sections
TASKS.md Current phase & task details 2 min Current phase section
CLAUDE.md AI-specific rules & workflows 5 min Critical Rules, Config Formats, TDD
docs/prd.md Detailed specifications 10 min Section 2 (Config Formats), relevant sections
docs/config.md Project configuration values 1 min All fields

3. Task Execution Workflow (TDD)

1. Read task from TASKS.md
2. Check phase dependencies (previous phases must be complete)
3. Read relevant documentation sections
4. **WRITE TESTS FIRST** (cli/test/[module].test.ts)
   - Use vitest + mock-fs
   - Cover all edge cases
5. Implement code (src/[module].ts)
   - Follow patterns in CLAUDE.md
   - Match config formats EXACTLY (see PRD Section 2)
6. Run tests: pnpm test
7. Verify: pnpm typecheck && pnpm lint
8. Mark task [x] in TASKS.md
9. Update phase status if phase complete
10. Commit with Angular convention

4. Critical Implementation Rules

Config Format Precision (see PRD Section 2.2):

Read the full file on GitHub · 356 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 · 356 lines · 10 tokens per session scan A b9b88e62afc0

Subscribe to this mod's changes

do-task is a command published in the GitHub repository nicepkg/vsync (57 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 2,777 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.

Related

Other commands, from other repositories