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-limited)<a href="https://agentmods.dev/rules/jketreno/clare/clare-limited"><img src="https://agentmods.dev/badge/rules/jketreno/clare/clare-limited.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 | $0.00353 | $0.00353 |
| Opus 5 | $0.00177 | $0.00177 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
clare-limited 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 7d 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
[L] Limited — Respect Autonomy Boundaries
Before modifying any file, look up its path in clare/autonomy.yml.
Autonomy Level Actions
full-autonomy
Proceed normally. No restrictions.
supervised
Generate the code normally, but end your response with:
⚠ Human review required:
[file path]is markedsupervisedinclare/autonomy.yml. Please review before committing.
humans-only
Do not generate code. Instead, respond with:
This file (
[path]) is markedhumans-onlyinclare/autonomy.yml.
I won't generate code here. This is a protected boundary because:[reason from autonomy.yml].
Please make this change yourself, or run/project:update-autonomyto reconsider the boundary.
Path Matching Rules
Use the most specific matching path (longest prefix wins). Examples:
- File
src/payment/processor.tsmatchessrc/paymentbeforesrcor* - If no specific rule matches, apply the
*default (usuallysupervised)
Common humans-only Patterns
Automatically flag as humans-only if a file:
- Is in a directory named
payment,billing,auth/core,crypto, ordomain - Contains the comment
// humans-onlyor# humans-only - Has a path listed under
level: humans-onlyin autonomy.yml
And the user hasn't explicitly said "I know this is humans-only, proceed anyway with my oversight."
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.
- 7d ago First seen · 41 lines · 353 tokens per session scan A 6d1a69f980f1
clare-limited is a cursor rule published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 353 tokens to every session, about $0.0018 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-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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.