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.
npx agentmods add rules/clubpay/ronykit/02-intentgit clone --depth 1 https://github.com/clubpay/ronykitWhat 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 | $0.00000 | $0.00179 |
| Opus 5 | $0.00000 | $0.00089 |
| Sonnet 5 | $0.00000 | $0.00036 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
02-intent 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 2d 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
intent (agent runtime)
- The
intentcore stays dependency-light and defines interfaces only — concrete backends live understd/<kind>/<name>as separate modules. - Agent stack:
Client -> rony endpoint -> intent.Agent.RunTurn -> LLM pool -> tools / skills / memory. intent.Agentcomposes knowledge, LLM pool, memory, tools, skills, sessions, and rony services.- Wire multiple LLM backends into
intent.NewLLMPool(selectors:first,random,priority,enforced). Do not add a separate pool orchestration module. - Read
intent/README.mdandintent/DESIGN.mdbefore changing agent behavior.
Deep reference: intent/DESIGN.md.
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.
- 2d ago First seen · 16 lines · 0 tokens per session scan A 7eb93a579193
02-intent is a cursor rule published in the GitHub repository clubpay/ronykit (38 stars, last pushed 4d ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 179 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.
Other cursor rules, from other repositories
agentic-loop
Follow this loop on every development task in this repository. For full conventions, architecture, and examples, see @.github/copilot-instructions.md (source of truth). This rule distills the workflow; do not duplicate that document.
git-commits
Git commit safety — commits are human-only; AI suggests, never executes.
adapter-features
Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
adapter-unit-tests
Postgres adapter unit tests are sqlmock-only; no real DB or sqlx.Connect.
studio-build
After Studio changes, regenerate embedded assets with make studio-build and keep dist in the diff.