desplega

A thin wrapper that invokes the `desplega:brainstorming` skill with autonomy controls.

Analyze the codebase and automatically add Business-Use SDK instrumentation to track critical business flows.

You are tasked with creating git commits for the changes made during this session.

Continue work from a saved handoff file

A thin wrapper that invokes the `desplega:planning` skill with autonomy controls.

A thin wrapper that invokes the `desplega:tdd-planning` skill with autonomy controls.

A thin wrapper that invokes the `desplega:implementing` skill with autonomy controls.

A command that invokes the `desplega:learning` skill to manage institutional knowledge.

A thin wrapper that invokes the `desplega:qa` skill with autonomy controls.

One-shot question answering using the research process

A thin wrapper that invokes the `desplega:researching` skill with autonomy controls.

A thin wrapper that invokes the `desplega:reviewing` skill with autonomy controls.

Execute a single plan phase as a background sub-agent

A thin wrapper that invokes the `desplega:verifying` skill with autonomy controls.

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the location of files, it will also give you code details!

Use this agent when you need to preserve context before running out of context window space, when you want to checkpoint progress on a complex task, when transitioning between sessions, or when explicitly asked to save/store current progress. Examples: <example> Context: The assistant has been working on a complex refactoring task and notices the conversation is getting long. user: "Continue refactoring the authentication module" assistant: "I notice we've been working on this refactoring for a while and the context is getting substantial. Let me use the context-handoff agent to save our progress before continuing." <commentary> The assistant proactively recognizes context accumulation and uses the context-handoff agent to preserve state before it becomes a problem. </commentary> </example> <example> Context: User explicitly wants to save progress. user: "Let's save where we are - I need to take a break" assistant: "I'll use the context-handoff agent to document our current progress and state so we can resume seamlessly later." <commentary> User explicitly requests saving progress, triggering the context-handoff agent. </commentary> </example> <example> Context: Assistant is about to hit context limits on a long debugging session. assistant: "We've made significant progress debugging this issue. Before we potentially lose context, let me use the context-handoff agent to capture everything we've learned and our current state." <commentary> Proactive handoff when approaching context limits during complex work. </commentary> </example> <example> Context: Completing a logical phase of work. user: "Great, the API endpoints are done. Now let's work on the frontend." assistant: "Perfect - the API work is complete. Let me use the context-handoff agent to document what we accomplished before we shift focus to the frontend." <commentary> Using handoff at natural transition points between phases of work. </commentary> </example>

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagent_type today to find any and all answers to your questions! It will research deeply to figure out and attempt to answer your questions! If you aren't immediately satisfied you can get your money back! (Not really - but you can re-run web-search-researcher with an altered prompt in the event you're not satisfied the first time)

Interactive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.

Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.

Compounding knowledge across projects and teams. Captures, searches, and promotes institutional learnings via tiered backends (local/qmd/agent-fs).

Execute individual plan phases as background sub-agents for context-efficient implementation.

Implementation planning skill. Creates detailed technical plans through interactive research and iteration.

Functional validation skill. Captures test evidence (screenshots, recordings, links) and produces QA reports in thoughts/*/qa/.

One-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research.

Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.

Structured critique of research, plan, and brainstorm documents for completeness, gaps, and quality.

TDD-focused implementation planning. Creates plans with strict Red-Green-Commit/Rollback cycles for each step.

Post-implementation plan verification. Cross-references plans against actual changes for completeness and accuracy.

1 hook across 1 event