watchboard

Post-implementation business assessment by Prometeo (PM). Verifies success metrics achievement, scope compliance, acceptance criteria business interpretation, risk materialization, and product decision closure. Outputs structured report with verdict and confidence score.

Analyzes checklist effectiveness by tracking hit rates, identifying stale items, and finding coverage gaps. Generates evolution suggestions following Boorman's principles. Use periodically to keep checklists field-tested and relevant.

Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Use periodically or before releases to maintain code hygiene.

Creates a complete product feature specification. Use when defining new features, writing user stories, or planning product work. Generates structured specs in docs/specs/.

Generates test cases for a module or function following FIRST principles and Arrange-Act-Assert pattern. Detects test framework from project config. Use to bootstrap test coverage for existing code or as the Red phase of TDD.

Create and manage git worktrees for isolated feature work. Use when starting implementation that should not touch the main workspace, or for parallel development. Handles creation, baseline verification, and cleanup.

Implements a feature from its specification. Reads the spec, designs architecture, writes code, tests, and documentation. Use after a feature spec has been approved.

Handle code review feedback with technical rigor — verify before implementing, push back when reviewer is wrong, no performative agreement. Use when receiving feedback from Centinela, external reviewers, or PR comments.

Rebuilds the codebase knowledge index at docs/codebase-index.json. Scans all source files for module structure, exports, dependencies, and tech debt hotspots. Shared across all three agents.

Pre-release verification with structured report. Validates test coverage, security status, CHANGELOG completeness, dependency freshness, tech debt severity. Outputs GO/NO-GO recommendation with confidence score and specific remediation steps.

Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification.

Deep security audit of code, dependencies, and infrastructure. Checks OWASP Top 10, authentication, authorization, data protection, and dependency vulnerabilities. Use before releases or after significant changes.

Inline verification for any written artifact — specs, plans, reviews, docs. Runs 4 checks in under 60 seconds. Use on demand outside the triforce flow, or rely on TIME OUT checklists during normal agent operations.

Runs controlled failure simulations to verify that agents correctly invoke their Non-Normal (emergency) checklists. Available scenarios: ambiguous-spec, failing-tests, security-finding. All outputs are labeled SIMULATION MODE and written to docs/training/.

Execute an implementation plan by dispatching fresh subagents per task with two-stage review (spec compliance, then code quality). Use for ad-hoc plan execution outside the full triforce ceremony.

4-phase root cause debugging process. Use when encountering any bug, test failure, or unexpected behavior BEFORE proposing fixes. Prevents guess-and-check thrashing. Includes root-cause tracing, defense-in-depth, and architecture questioning.

Generates a spec-to-implementation traceability matrix linking acceptance criteria from specs to implementation files, test cases, and review findings. Supports IEEE 830 compliance audits.

Verify work is actually done before claiming completion. Run verification commands, see passing output, confirm behavior. Evidence before assertions. Use before committing, creating PRs, or claiming a fix works.

Browser-based companion for showing mockups, diagrams, wireframes, and visual comparisons during design conversations. Uses chrome MCP tools. Falls back to text-only if unavailable. Use during brainstorming or any visual design work.