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/fmflurry/settings-opencodeWrote 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/fmflurry/settings-opencode/question-handling)<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/question-handling"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/question-handling/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/fmflurry/settings-opencode/question-handling"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/question-handling.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 | $0.00770 | $0.00770 |
| Opus 5.5 | $0.00308 | $0.00308 |
| Sonnet 5.5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
question-handling 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Question Classification & Handling
Blocking vs Non-Blocking
Subagents MUST classify every returned question as one of:
BLOCKING
- Agent cannot make ANY further progress without answer
- Next implementation step is unknowable
- Choosing between mutually exclusive paths
- Clarifying a contradiction (spec vs codebase, two docs conflict)
- The answer changes which files get touched
Format: [BLOCKING] <one dependency-safe question>
Tag in output: ## Blocker: <question>
NON-BLOCKING
- Agent can continue with a reasonable default
- Question is about quality, preference, or future scope
- Agent wants confirmation of a choice already made
- "Nice to have" improvements spotted during work
Format: [NON-BLOCKING] <question> (default: <what agent assumed>)
Tag in output: ## Note: <question> (assumed: <default>)
Conductor Protocol
On receiving blocking question:
- Attempt self-resolution: check repo (CodeMemory, codememory_claims, grep, read)
- If resolvable from cited repo/CodeMemory evidence (never inferred intent) → answer it, re-dispatch (
Agent) with answer folded into brief - If NOT resolvable →
AskUserQuestionimmediately
On receiving non-blocking question:
- Add to session accumulator (keep list in memory)
- Do NOT interrupt flow
- Continue with remaining tasks
At job completion (ALL dispatches done):
- Review accumulator
- Report ALL accumulated non-blocking questions to user:
## Questions Collected During Execution | # | From | Question | Assumed Default | |---|------|----------|-----------------| | 1 | coder | Use fetch or axios? | axios | | 2 | planner | Phase 2 needed before Phase 3? | Yes | Awaiting your input on any you'd like changed.
Socratic-First Resolution
Before surfacing ANY blocking question to user:
codememory_retrieve— semantic search for answercodememory_claims— user preferences/decisionsGrep/Read— verify exact files if CodeMemory is suggestive- If REPO CAN ANSWER (cite the evidence; never infer intent) → answer it, fold into re-dispatch brief
- Only if REPO CANNOT ANSWER →
AskUserQuestionwith socratic-design shape:- Evidence: what you found
- Question: single dependency-safe question
- Recommended: your best answer
- Why: reasoning
- If opposite: what changes
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 Changed · +9 tokens per session 83214fc08a06
- 4d ago Changed · +2 lines · +59 tokens per session f54ef3f471d0
- 8d ago First seen · 78 lines · 702 tokens per session scan A 934b0174e156
question-handling is a cursor rule published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 770 tokens to every session, about $0.0031 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 2026-10-08.
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.
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.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.