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/BetterTyped/hype-stackWrote 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/bettertyped/hype-stack/debugging)<a href="https://agentmods.dev/rules/bettertyped/hype-stack/debugging"><img src="https://agentmods.dev/badge/rules/bettertyped/hype-stack/debugging/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/bettertyped/hype-stack/debugging"><img src="https://agentmods.dev/badge/rules/bettertyped/hype-stack/debugging.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 | $0.00036 | $0.00313 |
| Opus 5.5 | $0.00014 | $0.00125 |
| Sonnet 5.5 | $0.00007 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
debugging scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If a test can't reach it, a script or curl invocation with a known-bad output counts — but name the command and run it red at least once before touching the fix. What it actually says
Debugging Discipline
Feedback loop first
Before hypothesizing about a bug's cause, build a repro that goes red on this bug — usually a failing test at the nearest seam:
- Backend: a failing integration test against the real Docker services.
- Frontend: a failing component test driven by
setMockresponses. - If a test can't reach it, a script or curl invocation with a known-bad output counts — but name the command and run it red at least once before touching the fix.
A fix without a red loop is a guess. If you genuinely cannot build a repro, say so explicitly, list what you tried, and ask the user for what's missing (logs, payloads, environment access) instead of proceeding on hypothesis alone.
Fix against the loop
- Form one hypothesis at a time and test it against the loop — don't shotgun changes across files hoping one lands.
- The fix is done when the red loop goes green and the surrounding suite still passes.
Every bug fix ships with a regression test
The repro test from step one stays in the codebase as the regression test. If a bug escaped, the test suite had a hole — the fix isn't complete until the hole is closed. Follow the standard testing rules for where it lives and how it's written.
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 · 26 lines · 36 tokens per session scan A 7b587d3b8d42
debugging is a cursor rule published in the GitHub repository BetterTyped/hype-stack (12 stars, last pushed 15d ago), licensed MIT. It adds 36 tokens to every session and 313 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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
mobx-devtools
Instructions for using MobX DevTools, including a browser extension and development component for inspecting application state changes.
mobx-strict-mode
Guidance for enabling MobX strict mode, which requires observable state changes to happen inside actions.
apollo-devtools
A debugging guide for Apollo Client DevTools, a browser extension for inspecting GraphQL requests and Apollo's local cache. It covers queries, mutations, subscriptions, variables, responses, and errors.
browser-diagnosis
Reproducing and diagnosing App Builder in the browser — SDV, Playwright scratch drivers, selection menu pitfalls, PUT counting. Use when debugging UI, selection, or interaction.
modus-modal-implementation-react
Critical implementation patterns for ModusWcModal in React.
modus-checkbox-value-inversion-react
Critical bug fix for ModusWcCheckbox value property inversion.