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.
git clone --depth 1 https://github.com/jketreno/clareWrote 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.
[](https://agentmods.dev/rules/jketreno/clare/clare-ephemeral)<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>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.
| Model | Per session | Once 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 |
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.
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-autonomyrule inclare/autonomy.ymlwith 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 syncproto-visualization.md— Update UI components from protobuf changesapi-endpoint.md— Generate an endpoint with rate limiting and testsreality-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:
- Write a skill file in
clare/templates/skills/documenting how to regenerate it - Add the regeneration command to
clare/verify-local.sh(under build checks) - Add an architecture test that detects drift between source and generated output
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.
- 6d ago First seen · 53 lines · 472 tokens per session scan A 9fe146c6aa98
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.