sentropic

Use when bringing the harness method to a NEW or non-sentropic repo — maps the repo's conventions into a harness profile so the same scope/branch/verify kernel applies anywhere.

Use before any creative/design work (a feature, a package, an evolution) — explores intent and design via the spec-ladder with multi-peer adversarial review BEFORE implementation.

Use on any bug, test failure, or unexpected behaviour BEFORE proposing a fix — runs the generic evidence-first root-cause loop.

Use when you have a spec/decisions and need an executable plan — writes a lot-based BRANCH.md from the template and completes with track for realization state.

Use when completing a feature, a design step, or before merging — runs a ≥2-peer consensus review and reconciles the findings, instead of a single rubber-stamp pass.

Use when adding or evolving tests for a feature/bugfix — applies the sentropic test-pyramid, scoped-test loop, environment isolation, and AI-flaky policy.

Load FIRST in any sentropic repo — establishes the harness method (branch/scope/test/debug/review/brainstorm/plan) and supersedes superpowers for those acts.

Verify modified files against branch allowed/forbidden/conditional paths (via @sentropic/harness)

Read and update folder executive summaries in AI-priorities and opportunity workspaces.

Read and update folders that group initiatives and workspace materials.

Review initiative gate criteria for a maturity-stage transition in AI-priorities and opportunity workspaces.

Read and update initiatives, including the legacy read/update initiative tools.

Read and update folder matrix configurations in AI-priorities and opportunity workspaces.

Read and update organization records in AI-priorities and opportunity workspaces.

Read product records attached to opportunity workspaces.

Read proposal and bid records in opportunity workspaces.

Read solution records attached to opportunity workspaces and initiatives.

Generate documents (DOCX, PPTX) from the chat context. Routes freeform sandbox code through the V8 host bridge, or invokes an injected DOCX template renderer.

Analyze comment threads in the current context and propose or execute resolution actions after explicit user confirmation.

Access documents attached to a context (organization, folder, initiative, chat session) with list, summary, content, and analyze actions.

Answer targeted questions over conversation history with evidence references.

Unified plan/todo/task runtime orchestration — create checklists, update TODO progression, and advance individual tasks.

Online web search and page-content extraction for current external information.

Cross-workspace navigation and discovery — list accessible workspaces and search initiatives across them.

Update rules and skills after a branch completes — absorb learnings, update patterns

Close a branch — final validation, PR creation, rules update, merge

Initialize a new feature branch with worktree, BRANCH.md from template, and environment setup

Launch a subagent with proper template, ports, branch verification, and user announcement

Run lot gate checks — typecheck, lint, and scoped tests for current lot

Investigate an API issue using logs, DB queries, and generation traces

Debug Chrome or VSCode extension issues — auth, tools, build, IPC

Create and run a Playwright scratch probe to reproduce and fix a UI bug

Debug SSE streaming, provider responses, and delta aggregation issues

Scaffold a new E2E Playwright test following project patterns

Scaffold a new API route following project patterns

Verify all 5 LLM providers when modifying provider or LLM runtime logic

Trace impact of a schema or service change across the codebase before modifying