agentleFS
ShiningPlagueShiningPlague/shiningplague-studio/skills/scope-check/SKILL.md

scope-check

Skill0 starsChanged 4 months agoMITView on GitHub

Use during implementation to detect scope creep — when work drifts beyond the current spec/plan/story. Fires during sprints, after plan tasks, or when the designer suspects deviation. Compares current work against the stated scope. ShiningPlague-adopted: full implementation with priority-ordered scope document lookup (plan / spec / story / workstream) and 20% drift heuristic.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 10 projects that use this

The file

Files
SKILL.md

Scope Check

🌱 ShiningPlague-adopted. Originally Donchitos (barebones stub); battle-tested on a shipped Godot project. Upstream was a pointer-only file; this version is the full implementation — priority-ordered scope doc lookup, 20% drift heuristic, park-or-expand proposal.

Detect scope deviation by comparing current work against the governing spec, plan, or story.

If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.

Procedure

1. Identify Governing Scope Document

Find the active scope document (in priority order):

  • Active plan: docs/plans/YYYY-MM-DD-*-plan.md with status 🚧 ACTIVE
  • Active spec: docs/specs/YYYY-MM-DD-*-design.md with status 🚧 IN PROGRESS
  • Active story: production/epics/<epic-slug>/*.md with status in-progress
  • Active workstream state: production/workstreams/<name>.md → "In Progress" section

2. Extract Stated Scope

From the governing document, extract:

  • What was planned to be built/changed
  • What was explicitly out of scope (if stated)
  • Expected outcomes at ship

3. Compare Against Current Work

git diff --stat + read changed files. For each change:

  • In scope — directly serves the stated plan
  • Adjacent — related but not stated (potential creep)
  • Out of scope — unrelated to current work

4. Assess Creep Risk

  • Count adjacent + out-of-scope changes
  • Estimate effort consumed on non-scope work
  • Flag if the ratio exceeds 20% (heuristic — adjust per context)

5. Output

## Scope Check: [governing document name]

### In Scope
- [change 1] ✓
- [change 2] ✓

### Adjacent (potential creep)
- [change 3] ⚠ — related but not in plan

### Out of Scope
- [change 4] ✗ — not related to current work

### Verdict
CLEAN — all work is in scope
or
DRIFT — [N] changes outside scope, [estimate] effort diverted

6. If Drift Detected

Propose to designer:

  • Park out-of-scope work in live_test_notes.top_of_mind_YYYY-MM-DD
  • Or expand scope (with explicit acknowledgment)
  • Or revert and refocus

Project Paths

  • Specs: docs/specs/
  • Plans: docs/plans/
  • Workstreams: production/workstreams/

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.