30 free prompts · all verified
Cursor prompts
Cursor-specific rules files, agent-mode task briefs and review prompts — written against Cursor 2.x behavior, with the constraint blocks that stop an agentic editor from wandering.
Every prompt lists the exact tool and version it was tested against.
Brief Cursor's Agent mode to build a multi-file feature without wandering into untouched filesA Composer/Agent-mode brief that names the files in scope, the data contract between them, the codebase's existing conventions, and what to leave alone, plus a forced pre-edit plan, so an autonomous multi-file build stays inside the feature you actually asked for instead of expanding into whatever the semantic index surfaces as related.Cursor 2.22026-08-05Force Cmd+K to change only the highlighted lines, not the whole block around themA Cmd+K inline-edit instruction that states the transformation, an explicit byte-identical preserve list, and a fallback rule for when the transformation can't be done cleanly, tuned for the selection-scoped inline editor rather than a whole-file Agent pass.Cursor 2.22026-07-22Point Cursor BugBot at the actual risk in a PR instead of a generic pass over the diffA PR description written for BugBot, Cursor's automated PR-review agent, that states risk areas and known trade-offs up front and defines exactly how findings must be classified and cited, so its comment thread concentrates on real logic and security risk instead of restating the diff or re-litigating a deliberate choice.Cursor BugBotCursor 2.22026-07-30Write a Background Agent brief that survives running with nobody watchingA self-contained task brief for Cursor's Background Agents — the async, remote-run agent mode — with success criteria, a conservative-default policy for ambiguity, and a reviewable-PR requirement, since no one answers follow-up questions while it works in an isolated container.Cursor Background AgentsCursor 2.22026-08-02Turn Cursor's Agent-mode checkpoints into a real rollback plan for a risky refactorA refactor brief that breaks a risky change into checkpoint-sized steps and tells the agent to stop and name the last good checkpoint on failure — instead of patching a bad step with a second speculative fix — plus a named rollback trigger phrase for mid-session use.Cursor 2.22026-08-06Tell Cursor which package actually owns a change in a multi-root monorepo workspaceA context brief for Cursor's multi-root workspace support that names the owning package, treats sibling packages as read-only context, and states shared-file boundaries, so semantic search across the flattened index doesn't cross package lines while looking for a similarly named symbol.Cursor 2.22026-07-24Turn a pasted design screenshot into a component built from your existing design systemA brief for pasting a screenshot or Figma export into Cursor's chat or Agent mode that locks the output to your existing component primitives and design tokens, names the interactions a static image can't show, and forces the model to flag anything it interpreted rather than measured.Cursor 2.22026-07-27Have Cursor's Agent mode write tests against the spec, not against whatever the code already doesAn Agent-mode brief for generating tests against documented behavior rather than the implementation as found, with a forced tripwire requiring the model to prove each test would actually fail if the behavior broke, so a passing suite means something.Cursor 2.22026-07-21Run a major dependency upgrade through Cursor's Agent mode in triage-migrate-verify stagesA staged upgrade brief that requires triage of every affected API usage against a stated breaking-changes list before any file changes, so the blast radius gets reviewed as a plan rather than discovered after the fact spread across dozens of already-applied edits.Cursor 2.22026-07-29Make Cursor's Agent mode audit its own diff for scope creep before you review itA post-edit review prompt that has the agent re-check every file it just touched against the original brief, itemizing an UNREQUESTED label for anything it can't cite the brief to justify, catching incidental reformatting hidden inside an otherwise legitimate multi-file diff.Cursor 2.22026-08-07Require Cursor's Agent mode to measure a slow path before it proposes a fixA measure-diagnose-fix brief that requires the agent to instrument and get real numbers on a slow code path before proposing any optimization, so a confident-sounding fix can't ship for a bottleneck that was never actually located, and any temporary instrumentation gets removed before the change is called done.Cursor 2.22026-07-23Write intent-first comments that steer what Cursor Tab predicts nextA commenting-style brief — for the top of a file or a project-wide note — that shapes forward-looking intent comments for Cursor Tab's predictive multi-line completion, and enforces consistent terminology, so its suggestions match your next step more often instead of guessing from indentation and generic patterns alone.Cursor 2.22026-07-20Author a Cursor Project Rule that actually gets applied instead of ignoredA brief for writing a .cursor/rules/*.mdc Project Rule with the correct rule type, glob scope, and description for triggering, so the rule reliably activates in the situations it's meant for instead of sitting in the repo unused because it was scoped or worded wrong.Cursor 2.22026-08-08Build a Cursor Notepad once so a recurring task stops needing a re-explained brief every timeA brief for authoring a Cursor Notepad — a reusable, @-mentionable context block — for a task that recurs often enough that re-typing the same constraints every session is itself the cost, with an explicit staleness check so the Notepad gets corrected the first time it drifts from reality instead of silently misleading every session after.Cursor 2.22026-07-26Scope Cursor's chat context with @-symbols instead of hoping the index finds the right filesA brief for composing a chat or Agent-mode request using explicit @Files/@Folders/@Docs/@Git references rather than relying on implicit semantic search, so the model reasons from exactly the sources you intend instead of whatever the embedding index ranks as closest.Cursor 2.22026-07-31Get an accurate architecture explanation out of Cursor's Ask mode without it trying to fix anythingA read-only Ask-mode brief that asks for an explanation of how a system actually works today, with explicit instructions to distinguish observed behavior from inferred intent and to flag anything that looks broken rather than silently proposing a fix, since Ask mode is for understanding, not editing.Cursor 2.22026-08-01Force Cursor's Agent mode to reproduce a bug before it proposes a fixA debugging brief that requires the agent to first write a failing reproduction of the reported bug and confirm it fails for the stated reason, before proposing any change, so a plausible-sounding fix can't ship for a cause that was never actually confirmed to be the real one.Cursor 2.22026-08-03Route a Cursor Agent task through a connected MCP server instead of letting it guess at an APIA task brief that names the specific MCP server and tool Cursor's Agent mode should call for a task that touches an external system, with an explicit fallback rule for when the tool's response doesn't match what was expected, so the agent doesn't silently paper over an unexpected result from a system it can't fully inspect.Cursor 2.2MCP2026-08-04Use Cursor's whole-codebase context to migrate a state-management library site-wide, not file by fileA brief for a large, cross-cutting library migration that leans on Agent mode's long-context codebase understanding to first produce a complete inventory of usage patterns before touching a single file, so the migration plan accounts for every variant of how the old library is actually used, not just the common case.Cursor 2.22026-07-25Keep a frontend/backend API contract change in sync across both sides in one Cursor Agent passA brief for a cross-stack change that states the contract change as the single source of truth both sides must match, with an explicit order of operations and a final cross-check step, so the backend and frontend don't drift out of sync the way they do when each side gets migrated in a separate, disconnected session.Cursor 2.22026-07-28Put guardrails on which terminal commands Cursor's Agent mode is allowed to auto-runA brief establishing which categories of terminal command the agent may run without asking, which require a stated reason first, and which are off-limits entirely for this session, so an agent with command-execution access doesn't run something destructive or irreversible under the umbrella of a broadly worded task.Cursor 2.22026-08-09Have Cursor's Agent mode explore an unfamiliar codebase and write the onboarding doc you don't haveA brief for using Agent mode's codebase-wide search and read access to produce a real onboarding document for an undocumented or under-documented repo, grounded explicitly in what the agent actually traced through the code rather than a generic description of what a project 'like this' would typically contain.Cursor 2.22026-08-06Run a security and secrets pass with Cursor's Agent mode before a PR goes up, not afterA pre-PR security review brief that has Agent mode check a diff for hardcoded secrets, injection risk, and unsafe trust of client input, with concrete severity classification and an explicit rule against writing a fix that just silences a warning without addressing the underlying risk.Cursor 2.22026-08-08Brief Cursor's Agent mode to design a REST endpoint from a contract, not from whatever shape falls out of the handlerA contract-first REST endpoint brief for Agent mode that pins down resource semantics, status-code mapping, and error-body shape before implementation starts, so the eventual handler matches an agreed contract instead of whatever shape came out naturally while wiring up the route.Cursor 2.22026-08-08Have Cursor's Agent mode rank competing causes before it touches a production bug it can't reproduce locallyA differential-diagnosis brief for incidents where local reproduction isn't available — it forces the agent to list multiple candidate causes, score each against the actual evidence in hand, and name the one piece of evidence that would distinguish the top two, instead of committing to the first plausible-sounding explanation.Cursor 2.22026-08-09Force Cursor's Agent mode to prove a refactor changed nothing observable before calling it doneA pure-structure refactor brief that requires a characterization test capturing current behavior, bugs included, before any code moves, and forbids any change that isn't reachable purely by renaming, extracting, or reorganizing — so a refactor stays a refactor instead of quietly becoming an unannounced behavior change.Cursor 2.22026-08-10Give Cursor's Agent mode a security invariant list before it touches an authentication flowA brief for modifying or extending an authentication or session flow that states non-negotiable security invariants up front and requires the agent to check its own diff against each one before finishing, so a working feature doesn't ship with a quietly weakened security check.Cursor 2.22026-08-11Pin Cursor's Agent mode to a genuinely typed utility, not one that leans on any to get through the edge casesA short, direct brief for a single TypeScript utility function or module that states its exact signature, generic constraints, and edge-case behavior up front, and forbids any or an unnarrowed unknown as a way to dodge a hard case, so the function actually gives callers the safety a utility is supposed to provide.Cursor 2.22026-08-12Brief Cursor's Agent mode to build a Node worker service that survives a restart mid-jobA brief for a Node.js background or queue-consumer service that states idempotency requirements, graceful shutdown behavior, and what 'processed' actually means, so Agent mode doesn't ship a worker that quietly double-processes a job or drops one on restart.Cursor 2.22026-08-13Give Cursor's Agent mode a performance budget to build inside, not a bottleneck to fix afterwardA brief for building a new feature against a stated performance budget from the start, requiring the agent to price each meaningful implementation decision against that budget as it goes, instead of optimizing only after something has already shipped and been measured as slow.Cursor 2.22026-08-14
