step-sizing

step-sizing is a cursor rule for coding agents from robertsfeir/atelier-pipeline. It costs 607 tokens per session, scanned A, original, Apache-2.0.

A set of checks for deciding whether an implementation step is small and clear enough to work on safely.

In plain words
What is it for?
Apply it after making a coding plan to check whether each step has one clear outcome, touches a manageable number of files, can be tested alone, and can be redone easily.
Why use it?
Large or vague steps are harder to test, review, redo, and undo. These checks help split work into independently verifiable pieces.

Cursor rule

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 rules/robertsfeir/atelier-pipeline/step-sizing
Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

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 step-sizing

README.md
[![agentmods](https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/step-sizing.svg)](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/step-sizing)
Your own site
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/step-sizing"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/step-sizing.svg" alt="Measured on agentmods" height="20"></a>
Per session 607 This file is loaded in full into every session.
When invoked 607 The same file — it is already loaded in full.
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 $0.00607 $0.00607
Opus 5 $0.00303 $0.00303
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00061 $0.00061

Measured 5d ago against content hash 5c78a1b9b39b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

step-sizing 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 5d 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.

.cursor-plugin/rules/step-sizing.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step Sizing Gate

After drafting the implementation plan, apply these five tests to each step. Steps touching 10+ files (files_to_create + files_to_modify) MUST pass all five. Steps under 10 files are reviewed at Sarah's judgment but should still pass.

# Test Question Fail Action
S1 Demoable Can you state what this step enables in one user-facing sentence? ("After this step, I can ___") Split along demo boundaries -- each demoable behavior becomes its own step
S2 Context-bounded Does Colby need <= 8 files (create + modify) to implement it? Extract excess files into a prerequisite or follow-up step
S3 Independently verifiable Can Poirot test this step without the next one existing? Split so each verifiable behavior is its own step
S4 Revert-cheap If Poirot fails it, can Colby redo it in one fresh invocation? Split until each piece is one-invocation sized
S5 Already small Is this step <= 6 files with one clear behavior? Do NOT split -- over-splitting wastes orchestration overhead

Evidence

Sub-slicing from ~15 files/step to ~8 files/step improved first-pass QA from 57% to 93% and reduced rework findings by 90% (same model, same pipeline, same project -- only variable was step granularity). Context window research shows LLM accuracy degrades above ~32k tokens of effective context.

Split Heuristics

When a step fails the gate, look for these seams:

Seam Example
CRUD separate from lifecycle/state machine Firm create/list vs suspend/archive
Read-only separate from mutations User search/list vs suspend/grant-PM
Foundation separate from first consumer Auth guard + layout vs audit log page
Security separate from config CRUD AI settings vs key encryption/rotation
Data pipeline separate from dashboard Cost event logging vs cost trend UI
Schema/job separate from UI Analytics aggregation vs metrics page

Read the full file on GitHub · 52 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. 5d ago First seen · 52 lines · 607 tokens per session scan A 5c78a1b9b39b

Subscribe to this mod's changes

step-sizing is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 607 tokens to every session, about $0.0030 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.