harness-engineering

Bootstraps a repository for the harness-engineered workflow by creating AGENTS.md, docs/specs, docs/spikes, docs/plans, docs/generated, and baseline tracking files aligned to the PLANS.md contract.

Opens/updates GitHub PRs, checks CI, responds to feedback, and merges after GO using gh CLI with explicit consent gates.

Captures paired browser bug evidence videos using agent-browser (`failure` before fix and `resolution` after fix), stores raw captures in `tmp/artifacts`, and supports minimal manual promotion for durable review evidence. Use for browser/UI bug fixes and release evidence.

Produces a PLANS.md-compliant executable plan from a spec. Use after intake.

Converts fuzzy requests into a concrete initiative spec in docs/specs using a single slug and measurable success criteria. Use at the start of non-trivial work.

Converts post-release outcomes into durable docs and mechanical guardrails, clears generated scratchpads, and archives the initiative plan for reuse.

Runs agent-first review fanout across correctness, architecture, security, data, and simplicity, then enforces priority gates before release verification.

Recurring doc-gardening agent that scans for stale or obsolete documentation that no longer matches real code behavior, then queues fix-up work.

Executes active ExecPlans using milestone-driven progress updates, parallel subagents, and evidence-backed verification.

Investigates open questions before planning by running parallel research across docs, codebase patterns, and external references, then updates initiative artifacts with evidence-backed findings.

Runs a time-boxed investigation or throwaway prototype to validate feasibility, reduce ambiguity, or compare approaches before planning. Use between spec and plan when the path forward is unclear.

Deep-analyzes accumulated tech-debt tracker items with scoring and context, then presents prioritized recommendations for the user to triage interactively.

Performs release-readiness verification with test evidence, invariant checks, rollback readiness, and go/no-go decision recording in the active plan.

Orchestrates a harness-engineered workflow across intake, research, spike, plan, implement, review, verify-release, learn, and doc-gardening using docs/specs, docs/spikes, and PLANS-compliant active plans.

Creates or validates an isolated git workspace (worktree or branch) so harness workflow execution does not collide with human in-flight changes.

Creates or edits repo runbooks in docs/runbooks/ with correct frontmatter (title/use_when/called_from), additive-only semantics, and predictable linkage so skills can automatically apply them.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.