do-skeletons-first

A coding rule for writing documented class and function skeletons before implementing their logic. Each stub includes type hints, return examples, notes about the intended flow, and a placeholder error.

In plain words
What is it for?
Use it when designing a new class, API, or module before the implementation is ready.
Why use it?
It lets someone unfamiliar with the system understand and implement each method from its documentation. It also prevents undocumented or loosely typed stubs.

Cursor rule for Cursor

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/featurefactory-io/mimir/do-skeletons-first
Clone the repo
git clone --depth 1 https://github.com/FeatureFactory-io/mimir

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 161 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 $0.00000 $0.00161
Opus 5 $0.00000 $0.00081
Sonnet 5 $0.00000 $0.00032
Haiku 4.5 $0.00000 $0.00016

Measured 3d ago against content hash 75f49c4ecc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-skeletons-first 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.

.cursor/rules/do-skeletons-first.mdc · 15 lines

What it actually says

The core principle is that the developer who has no knowledge of the system can implement methods/properties etc. following only documentation in the skeleton - think its like you are a designer defining the task for the implementer.

Do as follows:

  • Read .windsurf/rules/do-write-concise-methods.md
  • Read .windsurf/rules/keep-docstrings-consistent.md
  • Create class and method/function stubs and document them
  • Include full docstrings, return types (eg "-> list[str]", and sample return values (per global rules)
  • Use raise NotImplementedError() in each method.
  • Do not skip type hints or documentation
  • Add comments inside the methods pointing attention to the logic flow, exception handling, logging etc.
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 · 15 lines · 0 tokens per session scan A 75f49c4ecc7f

Subscribe to this mod's changes

do-skeletons-first is a cursor rule published in the GitHub repository FeatureFactory-io/mimir (13 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 161 tokens. 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.