avoid-scope-creep

avoid-scope-creep is a skill for Claude Code, Codex from aiming-lab/MetaClaw. It costs 43 tokens per session (173 once invoked), scanned A, original, MIT.

Guidance for keeping code changes limited to the requested task.

In plain words
What is it for?
It helps developers make focused fixes, avoid unnecessary edits, and report unrelated issues without changing them.
Why use it?
It prevents unrelated refactoring, cleanup, or extra features from making a small change harder to review and riskier to merge.

Skill for Claude CodeCodex

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

About the project

MetaClaw is an AI-agent system that learns from conversations and evolves its behavior over time. It provides memory and learning modes for users who want an agent that adapts across interactions, with support for multiple claw-based agent projects.

aiming-lab/MetaClaw · 3,496 stars · on GitHub · arxiv.org

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 skills/aiming-lab/metaclaw/avoid-scope-creep
Any agent
npx skills add aiming-lab/MetaClaw --skill avoid-scope-creep
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/MetaClaw

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 avoid-scope-creep

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiming-lab/metaclaw/avoid-scope-creep.svg)](https://agentmods.dev/skills/aiming-lab/metaclaw/avoid-scope-creep)
Your own site
<a href="https://agentmods.dev/skills/aiming-lab/metaclaw/avoid-scope-creep"><img src="https://agentmods.dev/badge/skills/aiming-lab/metaclaw/avoid-scope-creep.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 173 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 5.1 $0.00043 $0.00173
Opus 5 $0.00022 $0.00086
Sonnet 5 $0.00009 $0.00035
Haiku 4.5 $0.00004 $0.00017

Measured 6d ago against content hash f19d5c754627, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

avoid-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 6d 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.

memory_data/skills/avoid-scope-creep/SKILL.md · 16 lines

What it actually says

Avoid Scope Creep

Mistake pattern: User asks to fix a specific bug → you also refactor the function, rename variables, add docstrings, and restructure the file → harder to review, introduces new risk.

Rule: Only change what was asked. If you notice other issues while working, mention them as a note rather than silently fixing them.

Exception: If a requested change is impossible without fixing a directly blocking dependency, fix the minimum required dependency and explain why.

Anti-pattern: while I'm here, I also improved... without being asked.

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. 6d ago First seen · 16 lines · 43 tokens per session scan A f19d5c754627

Subscribe to this mod's changes

avoid-scope-creep is a skill published in the GitHub repository aiming-lab/MetaClaw (3,496 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 173 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 2026-08-30.

Related

Other skills, from other repositories

llama-factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.

davila7/claude-code-templates · 51 tokens

tinker-fine-tuning

Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.

synthetic-sciences/openscience · 62 tokens

tinker-training-cost

Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

synthetic-sciences/openscience · 55 tokens

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

synthetic-sciences/openscience · 63 tokens

colab-finetuning

Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.

synthetic-sciences/openscience · 67 tokens

llm-integration

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

yonatangross/orchestkit · 58 tokens