Agent
Independent, isolated code reviewer. Use to review a finished work product (a git diff against a plan/spec) for spec compliance and code quality before committing. Receives ONLY a path to the diff file, a path to the spec/plan and its acceptance criteria — never the implementation conversation. Returns a…
Agent
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! :).
Agent
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.
Agent
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.
Agent
Adversarial verifier for a single code-review finding. Use to test one finding before acting on it — it tries to refute the claim against the code. Receives ONLY a path to the diff file, a path to the spec/plan the finding is judged against, and exactly one finding verbatim — never the reviewer's other findings, its…
Agent
The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.
Agent
Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a researching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you…
Agent
Grades a draft sentence by sentence against the author's voice sample, returning one verdict per sentence and never replacement text. Dispatch it with the filled prompt template from df:deslop's references/voice-prober.md — the ladder, the draft, the sample, and the preserve list all travel in that prompt.
Agent
Researches information on the web. Use when you need information that isn't in the local codebase or your training data — modern APIs, current events, library changelogs, etc.