A Claude Code plugin for intent-driven development: brainstorm, design, plan, execute
Agent
Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…
Agent
Orchestrates /c-audit. Reads the plan + diff range + config, fans out one parameterized generic sub-agent per audit in the active roster (default + optional), synthesizes per-audit results into one structured report. Single shipped agent; per-audit sub-agents are dynamic invocations using audit-specific prompts from…
Agent
Sweeps a freshly generated set of design or plan child docs for cross-doc consistency after parallel generation. Reconciles trivial wording itself; surfaces substantive contradictions to the PM for the user to resolve. Dispatched once by /c-design (all-at-once mode) and /c-plan after generators return.
Agent
Implements one Cadence plan task per dispatch. Reads only the task block and the files in the task's Reads: block. Writes code, tests, commits. Returns one of four statuses (DONE / DONEWITHCONCERNS / NEEDSCONTEXT / BLOCKED) with a plain-English lead. Never reads the whole repo; never inherits parent session context.
Agent
Reviews an implementer's diff against the task spec. First of two review stages. Runs after every cadence-implementer DONE. Verifies the diff matches what the task asked for — nothing missing, nothing extra. Does NOT review code quality (that's cadence-code-reviewer's job). Returns Approve or a list of spec gaps with…