agent-pro

Brainstorming specialist. Use before implementing any feature, fix or cli design to discuss the approach with the user first. Plans data models, storage layouts, test scenarios, and expected outputs.

Produce LOOP_<YYYY-MM-DD>_<slug>.md — a real runnable repro/verify runbook from user logs or prose. Expands to precise CLI/URL ops, builds workspace tools, runs steps 1–4 for real, records SYMPTOM CONFIRMED or VERIFY PASS. Pair with run-the-loop for fixes. Use for /establish-a-loop, "establish a loop", or "create a debug loop".

Fix until done: goal + inspect script under script/debug/, then iterate implement → inspect until PASS. Use after establish-a-loop or standalone for /run-the-loop, "loop until done", "max effort", "don't stop until".

Clarification-phase followup. Use when the user mentions followup to stay in discussion mode without moving to implementation.

OpenAI-compatible HTTP mock server for testing agents without real LLM calls. Loads a JSON config of request→response exchanges and returns pre-configured responses. Use when writing doctests or integration tests for agent runners.

Incremental deduplication workflow: map overlapping implementations, plan a PR stack into shared packages, seal doctests, migrate callers without behavior change. Use when the user mentions consolidate, dedupe, shared package, move enrichment into dot-pkgs, eliminate duplication, or /consolidate-code. Pair with investigate (overlap map) and doctest-tdd (sealed tests → impl).

Check whether this is a sound fix, or suggest what is the most sound fix, and explain why

Prototype-before-production workflow for risky host integrations (sudo, privileges, system config). Use when a feature touches the real OS, when behavior must be proven with a small script before full implementation, or when the user mentions prototype verification, POC script, or verify-with-prototype. Run after investigate/followup and before doctest-TDD integration.

Intent router that classifies user input and delegates to the appropriate specialist agent or skill. Use this for any initial user message to determine the right next step before diving in.

Investigate observed behavior or effects that need explanation. Use when the user reports unexpected results, asks why something happens, or wants the causal chain behind a symptom.

Human-in-the-loop macOS debugging checkpoints. Use when automation needs a human to confirm UI state, report observations, or proceed through manual steps.

Human-in-the-loop macOS debugging checkpoints. Use when automation needs a human to confirm UI state, report observations, or proceed through manual steps.

Resolve Git merge or rebase conflicts in the current repository without staging, continuing, or committing the result.

Fast agent specialized for exploring codebases. Use this to quickly find files by glob patterns, search code for keywords with regex, or answer questions about the codebase. Specify thoroughness level: quick, medium, or very thorough.

Issue reproduction agent. Use this when you need to reproduce a bug or issue locally. It understands the situation, breaks down complex issues into steps, and builds minimal reproducible examples to isolate root causes.

Use when the user wants a decision-tree style test case design with inherited setup and per-leaf assertions.

Use when the user has a rough product or feature idea and wants it expanded into user stories, workflows, open questions, and implementation considerations.

Use when the user has a test-case-tree output and wants runnable Go tests plus stub implementation following Test-Driven Development.

Use when the user wants comprehensive user-facing end-to-end test scenarios for a feature description.