do-one-task

A workflow command that finds the next unfinished task and guides its implementation using Claude Code’s task tools. It also runs the listed testing and completion steps.

In plain words
What is it for?
Use it to pick the first available task, implement it, run validation, complete the project workflow, and mark the task finished.
Why use it?
It removes the repeated work of choosing a pending task, changing its status, and remembering the project’s completion process.

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/motlin/claude-code-plugins/do-one-task
Clone the repo
git clone --depth 1 https://github.com/motlin/claude-code-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 245 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 $0.00012 $0.00245
Opus 5 $0.00006 $0.00122
Sonnet 5 $0.00002 $0.00049
Haiku 4.5 $0.00001 $0.00024

Measured 2d ago against content hash 1f2f9ea4ed93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-one-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.

plugins/builtin-tasks/commands/do-one-task.md · 27 lines

What it actually says

Find and implement the next incomplete task using Claude Code's built-in task tools.

Task Implementation Workflow

Steps

  1. Find the task — Call TaskList to find pending tasks that are not blocked. Pick the first available task (lowest ID).

  2. Read the task — Call TaskGet with the task ID to read the full description.

  3. Mark as in progress — Call TaskUpdate to set status to in_progress.

  4. Implement the task

    • Think hard about the plan
    • Focus ONLY on implementing this specific task
    • Ignore TODO/TASK comments in source code
    • Work through the implementation methodically
    • Run appropriate tests and validation
  5. Complete the workflow — Run /orchestration:finish to execute the full completion pipeline (commit, then precommit, rebase, and simplify). It commits before running git test run HEAD, which refuses to run on a dirty tree.

  6. Mark the task complete — Call TaskUpdate to set status to completed.

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 · 27 lines · 12 tokens per session scan A 1f2f9ea4ed93

Subscribe to this mod's changes

do-one-task is a command published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 12 tokens to every session and 245 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.