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/398894496-arch/runtime36Wrote 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/398894496-arch/runtime36/ask-product)<a href="https://agentmods.dev/rules/398894496-arch/runtime36/ask-product"><img src="https://agentmods.dev/badge/rules/398894496-arch/runtime36/ask-product/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/398894496-arch/runtime36/ask-product"><img src="https://agentmods.dev/badge/rules/398894496-arch/runtime36/ask-product.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00311 | $0.00311 |
| Opus 5.5 | $0.00124 | $0.00124 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
ask-product 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 1mo 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
Ask as product
When the user starts work (not a short follow-up like "what does that mean"):
- Set
OBSIDIAN_VAULTto the vault root. - Run
python3 ~/.agents/skills/krouter-obsidian/scripts/ask_product.py ask --query "<user text>"(or the copy inside this clone’sskill/krouter-obsidian/scripts/). - If
trigger.askis set: askprompt, stop, wait for adopt / reject / defer. At most one. Do not start the task. - After they answer, run
ask_product.py record --file <Name.md> --decision adopt|reject|defer.recorddoes not writeactive. - If adopt: do the work. When it succeeds, run
ask_product.py promote --file <Name.md>. Onlypromotesetsstatus: active. On failure, mid-task reject, or a non-adopt decision: do not promote. trigger-miss/trigger-ambiguous/already-asked: do not ask; continue.
Triggers live on the provisional page (triggers: a; b) or 90 系统文件/自动化/ask-triggers.json. This clone does not ship someone else’s trigger table.
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.
- 1mo ago First seen · 18 lines · 311 tokens per session scan A 514d2d215675
ask-product is a cursor rule published in the GitHub repository 398894496-arch/runtime36 (37 stars, last pushed 1mo ago), licensed MIT. It adds 311 tokens to every session, about $0.0012 per session on Opus 5.5. 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 2026-09-04.
Other cursor rules, from other repositories
claude-obsidian
Portable rules for the claude-obsidian product and user vault workflows.
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.
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.