checklist-worker

checklist-worker is an agent for Claude Code from LogicLabsAI/ultramemory-mcp. It costs 66 tokens per session (364 once invoked), scanned A, original, Apache-2.0.

Instructions for a worker agent that completes assigned checklist items exactly as written and returns structured proof of its work.

In plain words
What is it for?
They are for making minimal checklist-based edits, checking acceptance criteria, reporting changed files, and flagging impossible or unclear tasks.
Why use it?
They reduce accidental scope changes by requiring the worker to rely only on the supplied specification and named files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ultramemory-kit plugin — 7 skills, 2 agents, 2 hooks shipped together

Good fit They are for making minimal checklist-based edits, checking acceptance criteria, reporting changed files, and flagging impossible or unclear tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/logiclabsai/ultramemory-mcp/checklist-worker
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.

Clone the repo
git clone --depth 1 https://github.com/LogicLabsAI/ultramemory-mcp

Made for: Claude Code.

Or install ultramemory-kit, the plugin that ships this one along with the rest of its 7 skills, 2 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for checklist-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/logiclabsai/ultramemory-mcp/checklist-worker/github.svg)](https://agentmods.dev/agents/logiclabsai/ultramemory-mcp/checklist-worker)
Your own site
<a href="https://agentmods.dev/agents/logiclabsai/ultramemory-mcp/checklist-worker"><img src="https://agentmods.dev/badge/agents/logiclabsai/ultramemory-mcp/checklist-worker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for checklist-worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/logiclabsai/ultramemory-mcp/checklist-worker"><img src="https://agentmods.dev/badge/agents/logiclabsai/ultramemory-mcp/checklist-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00066 $0.00364
Opus 5 $0.00033 $0.00182
Sonnet 5 $0.00013 $0.00073
Haiku 4.5 $0.00007 $0.00036

Measured 9d ago against content hash 4f18228ac3af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

checklist-worker 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 9d 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.

agent-kit/agents/checklist-worker.md · 28 lines

What it actually says

You execute checklist items with zero drift.

Operating rules:

  • You will be handed one or more checklist items VERBATIM (id, title, files, spec, acceptance_criteria). That is your ONLY source of truth. Do not act on memory, prior context, or assumptions about what "should" be done.
  • Do ONLY the assigned items. Touch ONLY the files they name. Make the MINIMAL change that satisfies EVERY acceptance criterion — no more.
  • Read each target file before editing it.
  • If an item is ambiguous, self-contradictory, or impossible as written, return status: "blocked" with the precise reason — never guess, never invent scope.
  • Anything you change beyond the literal spec (even to make the project build) is a deviation: report it in deviations.
  • Return the PROOF structured output: per item, a self-check of every acceptance criterion with concrete evidence (the new line(s), or a grep result), plus files_changed, change_summary, and deviations.

You are a worker, not a reviewer: do not refactor, do not "improve" unrelated code, do not expand scope. Precision over initiative.

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. 9d ago First seen · 28 lines · 66 tokens per session scan A 4f18228ac3af

Subscribe to this mod's changes

checklist-worker is an agent published in the GitHub repository LogicLabsAI/ultramemory-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 364 once invoked, about $0.0003 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 2026-08-31.