arnesto: Skill for Claude Code

.agents/skills/small-safe-steps/SKILL.md

small-safe-steps is a skill for Claude Code from saski/arnesto. It costs 71 tokens per session (3,206 once invoked), scanned A, a copy of small-safe-steps, Unlicense.

A planning skill that breaks large or risky engineering work into small steps, usually taking one to three hours each.

In plain words
What is it for?
It helps plan database changes, API changes, service replacements, and work that spans more than a day.
Why use it?
It makes migrations, refactors, and other changes easier to perform with less disruption.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is saski/arnesto's own configuration. It tells Claude Code how to work on arnesto itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything arnesto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saski/arnesto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saski/arnesto/main/.agents/skills/small-safe-steps/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

Made for: Claude Code.

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 small-safe-steps

README.md
[![agentmods](https://agentmods.dev/badge/skills/saski/arnesto/small-safe-steps.svg)](https://agentmods.dev/skills/saski/arnesto/small-safe-steps)
Your own site
<a href="https://agentmods.dev/skills/saski/arnesto/small-safe-steps"><img src="https://agentmods.dev/badge/skills/saski/arnesto/small-safe-steps.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00071 $0.03206
Opus 5 $0.00036 $0.01603
Sonnet 5 $0.00014 $0.00641
Haiku 4.5 $0.00007 $0.00321

Measured 3d ago against content hash c9f458efd5da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

small-safe-steps 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 3d 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.

Origin

This is a copy

91% identical to small-safe-steps — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/small-safe-steps/SKILL.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STARTER_CHARACTER = 🪜⚡

Small Safe Steps

Mission

Help you divide ANY work into the smallest, safest, most valuable steps possible — ideally 1-3 hours each.

Core belief: Risk grows faster than the size of the change.


How to Use This Skill

Automatic activation - just ask:

  • "How do I migrate from SendGrid to AWS SES?"
  • "I need to refactor this legacy code"
  • "How do I rename this database column safely?"
  • "What's the safest way to implement X?"

Manual invocation:

  • /small-safe-steps + describe your work
  • Example: /small-safe-steps Migrate authentication from Auth0 to Keycloak

In workflow with other skills:

  1. Use story-splitting → Break large story into smaller ones
  2. Use complexity-review → Simplify technical approach
  3. Use small-safe-steps (THIS SKILL) → Plan 1-3h implementation steps

When to Use This Skill

Use when:

  • Work feels too big or risky (refactoring, migrations, performance fixes)
  • Database schema changes, API changes, service replacements
  • User asks "how do I implement" after deciding what to build
  • Work will take more than 1 day

Do NOT use when:

  • User is still deciding WHAT to build (use story-splitting or hamburger-method first)
  • Work is already small (< 3 hours)
  • User asks for architectural review (use complexity-review instead)

Applies to ALL Types of Work

Product Work

  • Feature implementation
  • User stories (after initial splitting)
  • UX improvements

Technical Work

  • Refactorings
  • Performance improvements
  • Tech debt reduction
  • Architecture changes
  • Database migrations

Research & Investigation

  • Debugging complex issues
  • Spike/POC work
  • Technology evaluation
  • Root cause analysis

Operations & Deployment

  • Infrastructure changes
  • Service migrations
  • Deployment process improvements

Core Process

Step 1: Understand the Goal

Clarify the goal by asking:

  • "What's the end state we want?"
  • "Why are we doing this now?"
  • "What's the smallest outcome that would be valuable?"
  • "How will we know it's done?"
  • "What's the risk if this goes wrong?"

Read the full file on GitHub · 376 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 376 lines · 71 tokens per session scan A c9f458efd5da

Subscribe to this mod's changes

small-safe-steps is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 71 tokens to every session and 3,206 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to small-safe-steps, differing in 10 lines, and is treated as a copy.