scoping-cutting

scoping-cutting is a skill for Claude Code, Codex from liqiongyu/lenny_skills_plus. It costs 38 tokens per session (2,102 once invoked), scanned A, original, Apache-2.0.

A method for reducing a project to the smallest useful version that can fit a fixed amount of time.

In plain words
What is it for?
Use it to define an MVP, decide what to cut or defer, set non-goals, and establish rules for handling new requests.
Why use it?
It makes trade-offs explicit, limits scope creep, and keeps a project focused on testing its main assumption.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define an MVP, decide what to cut or defer, set non-goals, and establish rules for handling new requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liqiongyu/lenny_skills_plus/scoping-cutting
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.

Any agent
npx skills add liqiongyu/lenny_skills_plus --skill scoping-cutting
Clone the repo
git clone --depth 1 https://github.com/liqiongyu/lenny_skills_plus

Made for: Claude Code, Codex.

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 scoping-cutting

README.md
[![agentmods](https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/scoping-cutting/github.svg)](https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/scoping-cutting)
Your own site
<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/scoping-cutting"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/scoping-cutting/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 scoping-cutting

Your own site · 80×15
<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/scoping-cutting"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/scoping-cutting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,102 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 $0.00038 $0.02102
Opus 5 $0.00019 $0.01051
Sonnet 5 $0.00008 $0.00420
Haiku 4.5 $0.00004 $0.00210

Measured 9d ago against content hash 891c4c617d56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

scoping-cutting 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.

skills/scoping-cutting/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scoping & Cutting

Scope

Covers

  • Converting a fuzzy initiative into a ship-able slice that fits a fixed time budget (“appetite”)
  • Creating a cut list (what to drop/defer) with explicit trade-offs and rationale
  • Defining an MVP as a hypothesis test (what you’re validating, not just “smaller”)
  • Choosing a Minimum Lovable Slice (viable and emotionally resonant) instead of a “barely works” release
  • Using Wizard-of-Oz / concierge approaches to validate value before building full automation
  • Preventing scope creep via explicit non-goals + change control

When to use

  • “Cut scope / descope this feature so we can ship by .”
  • “Define an MVP for this initiative (what hypothesis are we testing?).”
  • “We have 2–6 weeks; what can we ship that still matters?”
  • “Scope creep is killing us; define what’s in/out and how changes happen.”
  • “We need a minimum lovable version, not a compromised mess.”

When NOT to use

  • You don’t yet know what problem you’re solving (use problem-definition)
  • You’re choosing between many competing initiatives (use prioritizing-roadmap)
  • You need a decision-ready PRD with requirements (use writing-prds) or a build-ready design/tech spec (use writing-specs-designs)
  • You’re setting long-term product strategy or vision (use defining-product-vision)
  • You already have a scoped slice and need a timeline/milestone plan with stakeholder cadence (use managing-timelines)
  • You’re planning the actual launch/release (rollout, rollback, monitoring) for an already-scoped feature (use shipping-products)

Inputs

Minimum required

  • The initiative/feature and the decision (ship vs defer vs stop) + target date or time budget
  • Target user/segment + the core user journey you want to improve
  • Success metric(s) + 2–5 guardrails (trust, quality, cost, latency, support load)
  • Constraints and non-negotiables (legal/privacy, platform, dependencies, team size)
  • Candidate scope items (bullets are fine) + known unknowns

Read the full file on GitHub · 137 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. 9d ago First seen · 137 lines · 38 tokens per session scan A 891c4c617d56

Subscribe to this mod's changes

scoping-cutting is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,102 once invoked, about $0.0002 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 2026-09-03.