claude_harness_eng_v4

Discover and map an existing codebase before planning or changing it.

Change the behavior of existing code — story-driven by default, or --issue N for a GitHub bug fix. Test-first, full verification, code review.

Use when a planned change touches persisted data shape — ORM models, migration files, schema definitions, serialized formats, or message contracts — in /change, /refactor, or /implement on an existing codebase. Routes schema changes through expand-contract and proves reversibility before any deploy.

Generate production code and tests for a story group using agent teams for parallel execution.

Refactor existing code for quality, performance, or maintainability. Enforces core quality principles with ratchet gate.

Generate test plan, test cases, test data fixtures, and Playwright E2E tests mapped to acceptance criteria.

Use when bumping a dependency version — package.json, pyproject.toml, requirements, or lockfile changes — in an existing codebase. Classifies the bump, audits the usage surface from the code graph, and isolates the upgrade in its own proven commit.

Controlled small-change lane for low-risk fixes, docs, tests, and narrowly scoped edits without running the full SDLC pipeline.

Autonomous build loop with Karpathy ratcheting, GAN evaluator, and session chaining. Iterates story groups until all features pass or stopping criteria met.

Use when about to edit any existing (non-greenfield) symbol — before the first Edit/Write to production code in /refactor, /change, or /vibe — to learn which tests cover it and route uncovered code to pinning or sprouting.

Code generation quality principles — TDD, typing, error handling, logging, API integration, LLM integration.

Build a deterministic dependency graph of an existing codebase. AST-first for Python and React/JS/TS (stdlib ast + tree-sitter wheels — symbols with line ranges, routes, components, hooks, call/render edges, god-file skeletons, incremental --files patching); regex fallback for C#, Java, Go. Outputs JSON + ranked symbol map + Mermaid + metrics for downstream brownfield, refactor, and seam-finder skills.

Generate Docker Compose stack, Dockerfiles, environment config, and init.sh bootstrap script.

Identify the safest cut-points in an existing codebase for a planned change. Reads code-graph.json + a goal, ranks candidate seams by observability + funnel + read/write asymmetry, and outputs a prioritized list with evidence.

Use when committing any change that includes structural work (rename, move, extract, reorder) in an existing codebase — keeps refactor commits behavior-free and behavior commits refactor-free so regressions stay attributable.

Use when checking-coverage-before-change reports an UNCOVERED symbol you must edit — writes characterization (pin-down) tests at the nearest observable seam and verifies they bite before any production edit.

Use when a symbol that must change is UNCOVERED and unpinnable (seam score < 0.5, or a skeletons/-flagged god file with no clean boundary) — adds behavior in a new fully-tested unit instead of editing legacy code in place.

Run evaluator and security reviewer concurrently for comprehensive quality gate.

Generate system architecture, machine-readable schemas, and UI mockups. Spawns planner + generator concurrently.

Create a Business Requirements Document — from a Socratic interview, or grounded in a Functional Requirements Document via --frd (with a deterministic net-new/dropped gate). First step in the SDLC pipeline.

Decompose BRD into epics, stories, dependency graph, and feature list for agent team execution.

Full SDLC pipeline. Runs all phases end-to-end with human gates on phases 1-3.

Run the application and verify sprint contract criteria via API tests, Playwright interaction, and schema validation.

Publish approved Claude Harness dependency groups to Linear/Jira-compatible tracker tasks and write the local tracker mapping contract.

Verify agent-framework skill packs declared in project-manifest.json#framework_skill_packs and print normal-terminal install commands for missing packs. Use after /scaffold reports PENDING MANUAL INSTALL, after manually adding a pack to the manifest, or to verify all configured packs are present.

Bounded clarification gate for resolving product, domain, API, security, or architecture uncertainty without exhausting the user.