clare-ephemeral

clare-ephemeral is a cursor rule for Cursor from jketreno/clare. It costs 472 tokens per session, scanned A, original, MIT.

A rule for handling generated code: change the source files or definitions and generate the output again instead of editing the output directly.

In plain words
What is it for?
Use it when working with generated types, components, mocks, or schemas from sources such as models, protocol definitions, or API descriptions.
Why use it?
It prevents manual fixes from being lost the next time code is generated.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when working with generated types, components, mocks, or schemas from…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/jketreno/clare/clare-ephemeral
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.

Clone the repo
git clone --depth 1 https://github.com/jketreno/clare

Made for: Cursor.

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 clare-ephemeral

README.md
[![agentmods](https://agentmods.dev/badge/rules/jketreno/clare/clare-ephemeral.svg)](https://agentmods.dev/rules/jketreno/clare/clare-ephemeral)
Your own site
<a href="https://agentmods.dev/rules/jketreno/clare/clare-ephemeral"><img src="https://agentmods.dev/badge/rules/jketreno/clare/clare-ephemeral.svg" alt="Measured on agentmods" height="20"></a>
Per session 472 This file is loaded in full into every session.
When invoked 472 The same file — it is already loaded in full.
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 $0.00472 $0.00472
Opus 5 $0.00236 $0.00236
Sonnet 5 $0.00094 $0.00094
Haiku 4.5 $0.00047 $0.00047

Measured 6d ago against content hash 9fe146c6aa98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

clare-ephemeral 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.

.cursor/rules/clare-ephemeral.mdc · 53 lines

What it actually says

[E] Ephemeral — Generated Code Is Regenerated, Not Patched

If a file is generated, fix the source and regenerate. Never patch the output.

How to Identify Generated Files

A file is generated if:

  • It has a header comment: // @generated, # Generated by, // DO NOT EDIT, // Code generated
  • Its path is in a generated/, gen/, __generated__/, or .generated/ directory
  • Its path matches a full-autonomy rule in clare/autonomy.yml with a reason mentioning generation

What To Do Instead of Editing

Want to change Right approach
A generated TypeScript type Update the source (Pydantic model, proto, OpenAPI) and regenerate
A generated React component Update the protobuf or template and re-run the generation skill
A generated mock Update the OpenAPI/proto contract and regenerate mocks
A Zod schema Update the Pydantic model it derives from, regenerate

Regeneration Skills

Check clare/examples/skills/ for documented example regeneration workflows:

  • type-sync.md — Keep Python ↔ TypeScript types in sync
  • proto-visualization.md — Update UI components from protobuf changes
  • api-endpoint.md — Generate an endpoint with rate limiting and tests
  • reality-test.md — Generate reality tests against an external service

New skills belong in clare/templates/skills/.

When Asked to Modify a Generated File

Respond with:

This file appears to be generated ([reason]). I'll fix the source and regenerate rather than editing it directly.

Source to update: [source file] Regeneration command: [command or skill name]

Should I proceed?

Setting Up Regeneration

When creating a new generated file type:

  1. Write a skill file in clare/templates/skills/ documenting how to regenerate it
  2. Add the regeneration command to clare/verify-local.sh (under build checks)
  3. Add an architecture test that detects drift between source and generated output
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 · 53 lines · 472 tokens per session scan A 9fe146c6aa98

Subscribe to this mod's changes

clare-ephemeral is a cursor rule published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 472 tokens to every session, about $0.0024 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.