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/hlalljie/agent-workflow-presetsWrote 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/hlalljie/agent-workflow-presets/research-before-suggesting)<a href="https://agentmods.dev/rules/hlalljie/agent-workflow-presets/research-before-suggesting"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/research-before-suggesting/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/hlalljie/agent-workflow-presets/research-before-suggesting"><img src="https://agentmods.dev/badge/rules/hlalljie/agent-workflow-presets/research-before-suggesting.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 | $0.00269 | $0.00269 |
| Opus 5.5 | $0.00108 | $0.00108 |
| Sonnet 5.5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
research-before-suggesting 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 17d 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
Do not invent or assume features, flags, APIs, or config options exist. Do not claim something works based on "what makes sense."
When suggesting technical solutions involving library APIs, CLI tools, framework features, or packages:
- Search docs or web to verify it exists
- Confirm exact syntax and behavior
- Only then suggest it
When uncertain, say so and research first.
Applies to internal codebase too: Before creating a new component, folder, utility, or pattern, read the existing codebase to see how the same kind of thing is already done. Check docs/folder-structure.md, then read the nearest existing implementation. Do not assume a structure is correct because it "makes sense" — verify it matches what already exists.
Missing plan files: finished plans move to .cursor/plans-archive/<plan-name>/. If a path under .cursor/plans/ does not exist, check the same path under .cursor/plans-archive/ before treating it as gone.
If the question requires comparing options or making an architectural decision, use the research skill for a deeper investigation.
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.
- 17d ago Changed · +2 lines · +53 tokens per session 0f75f8763eeb
- 1mo ago First seen · 18 lines · 216 tokens per session scan A 2b698dcf19c8
research-before-suggesting is a cursor rule published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 18d ago), licensed MIT. It adds 269 tokens to every session, about $0.0011 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 2026-08-31.
Other cursor rules, from other repositories
incremental-verify
Verify each behavior before building the next. One test, one implementation, one commit. No bulk-writing tests for behavior that does not yet exist.
context-discipline
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).
pn-visual-indicator
Tag every pnCore-touched assistant response with a context tag plus 🔺 (red triangle emoji) so the response is visible at a glance in Cursor's chat UI.
pn-tool-risk-policy
MCP tool risk tiers, HITL gates, and when to use approvalcheckpoint and gatelogappend. Use for safety reviews and workflow audits.