moscow

moscow is a command for coding agents from neurofoo/agent-skills. It costs 0 tokens per session (502 once invoked), scanned A, original, MIT.

A command for sorting project items into four priority groups: Must have, Should have, Could have, and Won’t have. MoSCoW is a method for clarifying scope and deciding what can be deferred.

In plain words
What is it for?
It helps prioritize features, tasks, or requirements, explain why each item belongs in its group, and summarize how effort is distributed.
Why use it?
It turns an unsorted list into an agreed order of importance, making trade-offs easier when time, budget, or capacity is limited.

Command

Part of the prioritization-skills plugin — 3 skills, 3 commands shipped together

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/neurofoo/agent-skills/moscow
Clone the repo
git clone --depth 1 https://github.com/neurofoo/agent-skills

Or install prioritization-skills, the plugin that ships this one along with the rest of its 3 skills, 3 commands.

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 moscow

README.md
[![agentmods](https://agentmods.dev/badge/commands/neurofoo/agent-skills/moscow.svg)](https://agentmods.dev/commands/neurofoo/agent-skills/moscow)
Your own site
<a href="https://agentmods.dev/commands/neurofoo/agent-skills/moscow"><img src="https://agentmods.dev/badge/commands/neurofoo/agent-skills/moscow.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 502 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 $0.00000 $0.00502
Opus 5 $0.00000 $0.00251
Sonnet 5 $0.00000 $0.00100
Haiku 4.5 $0.00000 $0.00050

Measured 5d ago against content hash 06766a8c88ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

moscow 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 5d 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.

moscow/commands/moscow.md · 69 lines

What it actually says

MoSCoW Prioritization

Categorize items into Must have, Should have, Could have, and Won't have for clear scope and priorities.

Instructions

Take the list of items provided and sort them into MoSCoW categories. Be rigorous about what's truly a "Must"—if the project/goal can still succeed without it, it's not a Must.

Output Format

Context What are we prioritizing for? What are the constraints (time, budget, capacity)?

Prioritized List

Must Have (Critical)

Without these, the project fails or is pointless

  • [Item] — [Why it's a must]
  • [Item] — [Why it's a must]

Should Have (Important)

Significantly adds value; painful to omit but project survives

  • [Item] — [Value it adds]
  • [Item] — [Value it adds]

Could Have (Nice to Have)

Desirable if time permits; low impact if cut

  • [Item] — [Why it's optional]
  • [Item] — [Why it's optional]

Won't Have (Not This Time)

Explicitly out of scope; may revisit later

  • [Item] — [Why it's deferred]
  • [Item] — [Why it's deferred]

Effort Distribution

Category Items Est. Effort %
Must X ≤60%
Should X ~20%
Could X ~10%
Won't X 0% (deferred)

Red Flags

  • If Must > 60% of effort: scope may be too large
  • If no Won'ts: probably not being honest about constraints
  • If everything is Must: priorities haven't been set

Rationale Explain the key trade-offs made and the reasoning behind contentious categorizations.

Next Step What's the first Must item to tackle?

Guidelines

  • Ask "If we shipped without this, would we fail?" for each Must
  • Challenge "Musts" that are really "someone really wants this"
  • Make Won'ts explicit—avoids scope creep later
  • Consider dependencies (a Must might require a "hidden" Must)
  • Stakeholder alignment is essential—this isn't just your opinion

$ARGUMENTS

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. 5d ago First seen · 69 lines · 0 tokens per session scan A 06766a8c88ee

Subscribe to this mod's changes

moscow is a command published in the GitHub repository neurofoo/agent-skills (111 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 502 tokens. 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.