agentmods.dev

detecting-scope-creep

detecting-scope-creep is a skill for Claude Code from AInsteinsBR/renata. It costs 68 tokens per session (1,037 once invoked), scanned A, original, MIT.

A scope-control method for deciding whether a newly suggested capability belongs in the current feature. It compares the suggestion with the feature's included and excluded work before allowing the task to expand.

In plain words
What is it for?
Use it when someone suggests adding another feature, making an incidental fix, or working on something not covered by the current specification.
Why use it?
It helps prevent scope creep: extra work that consumes time and attention, increases risk, and can delay the planned feature.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the renata plugin — 3 skills, 33 commands, 6 agents, 2 hooks shipped together

not rated 10repo 19d ago A scan 68 tokens original MIT

Good fit Use it when someone suggests adding another feature, making an incidental fix, or working on something not covered by the current specification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ainsteinsbr/renata/detecting-scope-creep
View source ↗ AInsteinsBR/renata ainsteins.com.br
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 AInsteinsBR/renata --skill detecting-scope-creep
Clone the repo
git clone --depth 1 https://github.com/AInsteinsBR/renata

Made for: Claude Code.

Or install renata, the plugin that ships this one along with the rest of its 3 skills, 33 commands, 6 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 detecting-scope-creep

README.md
[![agentmods](https://agentmods.dev/badge/skills/ainsteinsbr/renata/detecting-scope-creep/github.svg)](https://agentmods.dev/skills/ainsteinsbr/renata/detecting-scope-creep)
Your own site
<a href="https://agentmods.dev/skills/ainsteinsbr/renata/detecting-scope-creep"><img src="https://agentmods.dev/badge/skills/ainsteinsbr/renata/detecting-scope-creep/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 detecting-scope-creep

Your own site · 80×15
<a href="https://agentmods.dev/skills/ainsteinsbr/renata/detecting-scope-creep"><img src="https://agentmods.dev/badge/skills/ainsteinsbr/renata/detecting-scope-creep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,037 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 $0.00068 $0.01037
Opus 5 $0.00034 $0.00518
Sonnet 5 $0.00014 $0.00207
Haiku 4.5 $0.00007 $0.00104

Measured 10d ago against content hash 4fa874f61c50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

detecting-scope-creep 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 10d 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/detecting-scope-creep/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detecting scope-creep before it happens

Scope-creep is the most common way to blow a phase deadline. Each "just one more little thing" costs time, attention, context, and risks the phase gate.

When this skill activates

Auto-activates when the context involves phrases like:

  • "Since I'm already here, I'll also..."
  • "While I'm at it, I can add..."
  • "It also makes sense to..."
  • "I'll just quickly fix..."
  • "We also need..."
  • The proposal mentions a capability not listed in the active feature spec

Procedure (3 steps)

Step 1 — Identify the active feature + read the scope

  1. Consult CLAUDE.md section 4 — what is the active anchor feature?
  2. Read the feature's docs/features/F<N>-*.md.
  3. Mentally list the IN scope and the OUT scope.

Step 2 — Classify the proposal

Which category does the newly proposed thing belong to?

  • (A) Within the IN scope of the active feature — OK. You may proceed.
  • (B) Within the explicit OUT scope — STOP. Don't do it now.
  • (C) Not mentioned in IN or OUT — gray area. Decide consciously.

Step 3 — According to the classification

(A) It's in the IN

Proceed. Nothing to do.

(B) It's in the explicit OUT

Decline clearly. Suggested response:

"This is marked as OUT scope in docs/features/F<N>-*.md. Reason: . If you've changed your mind, we can:

  1. Defer it to the next phase (F<N+1>).
  2. Open a new feature spec via /feature-spec if it has become a priority.
  3. Consciously update the current feature (move it from OUT to IN with justification).

For now, I'll follow the original scope."

(C) Gray area

Present the user with 3 conscious-decision options:

  1. Add it to IN now — if it's critical for the current phase. Update the feature spec.
  2. Defer to the next phase — record it via /todo or in the project backlog.
  3. Quick spike (/spike) — if the question is "is it even worth it?".

DO NOT code without an explicit decision.

Examples

Read the full file on GitHub · 101 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. 10d ago First seen · 101 lines · 68 tokens per session scan A 4fa874f61c50

Subscribe to this mod's changes

detecting-scope-creep is a skill published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 19d ago), licensed MIT. It adds 68 tokens to every session and 1,037 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.

Claude CodePlanningadrclaude-pluginprdproduct-management
Related

Other skills, from other repositories

prd-taskmaster

Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…

anombyte93/prd-taskmaster · 80 tokens

handoff

Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…

anombyte93/prd-taskmaster · 158 tokens

generate

Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…

anombyte93/prd-taskmaster · 91 tokens

write-prd

Write PRD — Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. Use when writing PRDs, defining product requirements, creating user stories with INVEST criteria, or building go/no-go decision frameworks.

yonatangross/orchestkit · 54 tokens

customise-workflow

Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…

anombyte93/prd-taskmaster · 137 tokens

discover

Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…

anombyte93/prd-taskmaster · 92 tokens