Agent Claude CodeCursor
Mirage and assumption detector for plans. Verify plan claims match the codebase before implementation; triggers on verify assumptions or detect mirages in plan.
not rated 13 3mo ago A 36 tokens
Agent Claude CodeCursor
E2E browser and UI verification for a scoped plan phase. Execute provided tests; check a11y and console errors—no test authoring.
not rated 13 3mo ago A 36 tokens
Agent Claude CodeCursor
Read-only codebase discovery. Use for mapping files, symbols, usages, and dependencies. Triggers on find relevant files, map usages of, or explore codebase structure.
not rated 13 3mo ago A 41 tokens
Agent Claude CodeCursor
Post-implementation verification gate. Use after a phase to validate correctness, tests, build, and security with evidence-backed findings. Read-only, no fixes.
not rated 13 3mo ago A 37 tokens
Agent Claude CodeCursor
Backend/core implementation for a scoped plan phase. Use when executoragent is CoreImplementer or for server-side, API, data layer work.
not rated 13 3mo ago A 35 tokens
Agent Claude CodeCursor
Cold-start executability simulation for plans. Use to verify the first 3 tasks are specific enough for a zero-context executor.
not rated 13 3mo ago A 33 tokens
Agent Claude CodeCursor
Adversarial plan auditor before implementation. Use for architecture, security, dependencies, rollback, and cold-start executability of the first 3 plan tasks.
not rated 13 3mo ago A 38 tokens
Agent Claude CodeCursor
CI/CD, containers, and infrastructure for a scoped plan phase. Requires explicit approval for destructive or production operations.
not rated 13 3mo ago A 28 tokens
Agent Claude CodeCursor
Evidence-linked research on codebase or technology. Use for research how X works, investigate Y, or find evidence for. Read-only.
not rated 13 3mo ago A 33 tokens
Agent Claude CodeCursor
Technical documentation and diagrams for a scoped plan phase. Use for docs, ADRs, Mermaid, code-doc parity—not feature code.
not rated 13 3mo ago A 33 tokens
Agent Claude CodeCursor
Frontend/UI implementation for a scoped plan phase. Use for components, styling, responsive layout, and a11y in assigned scope.
not rated 13 3mo ago A 33 tokens
Cursor rule Cursor
Core ControlFlow identity, source hierarchy, and offline validations for the repository.
not rated 13 3mo ago A 211 tokens
Cursor rule Cursor
Rules for documentation parity, localized tutorials, and eval verification.
not rated 13 3mo ago A 0 tokens
Cursor rule Cursor
Guidelines for implementation, testing, review, and governance alignment.
not rated 13 3mo ago A 0 tokens
Cursor rule Cursor
ControlFlow orchestration: state machine, tier routing, Task delegation to controlflow subagents.
not rated 13 3mo ago A 0 tokens
Cursor rule Cursor
Rules for planning, scope discipline, and plan artifact tracking.
not rated 13 3mo ago A 0 tokens
Cursor rule Cursor
Guidelines for external host adaptation, portable plugins, and routing.
not rated 13 3mo ago A 0 tokens
Skill Cursor
Use when a saved plan may contain hidden assumptions disguised as facts, especially for medium or large tasks, unresolved high-risk plans, or plans that mention files, APIs, versions, integrations, tests, or concurrency patterns that should be verified against the repository before execution.
not rated 13 3mo ago A 59 tokens
Skill Cursor
Use when a saved plan should be tested for cold-start executability before coding, especially for large tasks, weak-confidence plans, or plans whose early phases may be too vague for a fresh executor to follow without hidden context.
not rated 13 3mo ago A 52 tokens
Skill Cursor
Use when work spans many turns or phases and you need durable notes, active-objective tracking, or context compaction without letting stale memory override the current codebase.
not rated 13 3mo ago A 40 tokens
Skill Cursor
Use when executing an approved multi-phase plan in Cursor, with gates, approvals, retries, and Task delegation to controlflow subagents.
not rated 13 3mo ago A 33 tokens
Skill Cursor
Use when a saved implementation plan should be adversarially reviewed before coding, especially for small, medium, or large tasks that may contain architecture flaws, scope gaps, destructive risk, weak rollback, weak tests, or dependency conflicts.
not rated 13 3mo ago A 52 tokens
Skill Cursor
Use when a repository task needs a strict ControlFlow-style implementation plan before coding, especially for small, medium, or large scope, cross-file edits, risky migrations, architectural uncertainty, or any work that should produce a saved Markdown plan artifact in plans/.
not rated 13 3mo ago A 55 tokens
Skill Cursor
Use when asked to review code, a diff, or a completed phase, especially when the result should emphasize bugs, regressions, validation status, and evidence-backed findings instead of style commentary.
not rated 13 3mo ago A 42 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: