claude-plugins

Use before subagent dispatch, before editing code that changes a struct, function signature, or API contract, or after a tool response contradicts the plan. Appends friction (F-N) and wins (W-N) to the project's session-log tracker.

Designing test suites, coverage gaps, flaky tests, asserting correctness

Use when asked to run a tracker hygiene sweep, audit tracker staleness or drift, clean up docs/trackers, before backlog triage or any "what's open?" report, or when the SessionStart banner says a tracker hygiene sweep is overdue. Interactive — every finding is human-gated; approved fixes apply via the librarian; each sweep appends to the project's tracker-hygiene-log.

Auditing codescout tool-call usage — inefficient tool patterns, recurring frictions, hookify candidates

Improving a prompt — critique, drafting from scratch, diagnosing model misbehavior, or coaching toward eval-driven iteration

Use when the user runs /research-subagent or asks for deep research, a full report, or research where the main context should not absorb raw search results — including mapping a broad subject across multiple angles (fan-out). Spawns one or more general-purpose subagents that call the researcher MCP and return only synthesized findings. Prefer /research-web for quick inline lookups.

Use when the user runs /research-web or asks for web research on a topic, person, company, library, market, or jobs and wants results inline in the current conversation. Calls the researcher MCP directly; results land in main context. Prefer /research-subagent if context is precious or the user asked for a deep/report mode search.

Reference guide for /research-web and /research-subagent — do not invoke directly. Provides the tool-selection matrix, mode guide, context budgets, and the shared research brief template used when calling the researcher MCP server.

System boundaries, module design, interface decisions

ML data hygiene, evaluation integrity, train/test leakage (lens required: classic or llm)

Bug resists surface fixes, flaky tests, failure doesn't match symptom

Technical writing, documentation architecture

Training loops, inference parity, ML pipeline issues

Profiling, latency, throughput, optimization

Work planning, task sequencing, breaking down large efforts

Structural code transformation, cleaning up tangled code

Security review, threat modeling, vulnerability analysis

Use when you explicitly want a READ-ONLY exploration of a DIFFERENT repo than the current one, returned as a structured findings report. Dispatches a subagent at the target repo; the explore-inject hook auto-bootstraps that project's CLAUDE.md + codescout memories. Routine cross-repo dispatches do NOT need this — the hook bootstraps them automatically.

Use when starting a new feature from scratch, converting an idea to a merged PR, or resuming work on an existing spec/plan. Triggers: "full lifecycle", "idea to PR", "new feature end-to-end", "resume sdd-flow", or explicit /sdd-flow invocation.

Use when starting a new feature from scratch, converting an idea to a merged PR, or resuming work on an existing spec/plan. Triggers: "full lifecycle", "idea to PR", "new feature end-to-end", "resume sdd-flow", or explicit /sdd-flow invocation.