claude_harness_eng_v5

Plugin claude_harness_eng_v5 from marketplace claude-harness-local in cwijayasundara/claude_harness_eng_v5. Commands read from the repo's manifest — 1 month ago.

Skills (47)

• advise

  Invoke the frontier advisor for a structural re-rank / unblock / design pivot. Compact brief only.

• agent-readiness

  Show how mature/safe this codebase is for heavy AI-agent use — a synthesis dashboard across 8 pillars, aggregating signals the harness already collects. Read-only report; aggregates state already on disk.

• attestation

  Generate a per-commit, durable compliance attestation (with a sha256 corruption-detecting integrity checksum) from the harness control inventory, the branch-protection/deploy-gate verify outputs, the gate verdict, and the ratchet baselines — then commit the record. Use at /gate or in CI to produce c

• author-prompt-surface

  Use when creating or editing .claude/agents/*.md, .claude/skills/*/SKILL.md, or .claude/commands/* — apply docs/prompting-standards.md (trigger conditions, model-agnostic bodies, no reasoning-as-text, effort floors).

• auto

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

• brd

  [Internal pipeline stage — run by /build; invoke directly only as a power user.] 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.

• brownfield

  Discover and map an existing codebase before planning or changing it. Add --seams "<goal>" to also rank the safest cut-points for that goal.

• change

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

• checking-coverage-before-change

  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. [Internal discipline — applied automatically by pipeline agents mid-task; dir

• checking-migration-safety

  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.

• clarify

  [Internal pipeline stage — run by the planning stages; invoke directly only as a power user.] Bounded clarification gate for resolving product, domain, API, security, or architecture uncertainty without exhausting the user.

• code-gen

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

• code-map

  [Internal pipeline stage — run by /brownfield and /seam-finder; invoke directly only as a power user.] Build a deterministic dependency graph of an existing codebase. AST-first for Python, React/JS/TS, and Java/C#/Go (stdlib ast + tree-sitter wheels — symbols with line ranges, routes, components, ho

• context

  Build a bounded, cited context pack from the living DeepWiki/code-map before broad source reads. Use in brownfield lanes and whenever source orientation could otherwise require large file reads.

• deepagents-code

  Build long-running, production-ready agents with DeepAgents — the opinionated harness on top of LangGraph/LangChain providing filesystem access, task planning, subagent delegation, and context management out of the box. Use for long-running coding/research/multi-step tasks where you'd otherwise hand

• deploy

  [Internal pipeline stage — run by /build; invoke directly only as a power user.] Generate Docker Compose stack, Dockerfiles, environment config, and init.sh bootstrap script.

• design

  [Internal pipeline stage — run by /build (use --doc-only standalone for an ARB narrative); invoke directly only as a power user.] Generate system architecture, machine-readable schemas, and UI mockups. Spawns planner + generator concurrently.

• evaluate

  [Internal pipeline stage — run by /auto and /gate; invoke directly only as a power user.] Run the application and verify sprint contract criteria via API tests, Playwright interaction, and schema validation.

• fastapi-code

  Build FastAPI backends — dependency injection with Depends(), Pydantic v2 request/response validation, async vs sync route rules, background tasks, and testing with TestClient. Use for any FastAPI route, dependency, or Pydantic model. Not for database/ORM design (no SQLAlchemy content here) or non-F

• feature

  Brownfield change route — take an existing-code feature request from intent to a reviewed PR, scaling from a single /change to an epic via /spec→/design→/auto. Linear-tracked, backed by a committed DeepWiki.

• fix-from-diagnostics

  [Internal pipeline stage — run by /auto self-heal and /implement validation when lint/type error volume is high; invoke directly only as a power user.] Turn compiler/linter output into a sharded work queue; fix per package with optional adversarial review — no full monorepo suite mid-shard.

• gate

  Run the adaptive pre-merge quality gate: deterministic checks, evaluator, diff review, and security review only when the diff crosses a security/data/API boundary. (Renamed from /review to avoid colliding with Claude Code's native /review PR-review command.)

• implement

  [Internal pipeline stage — run by /auto (follow with /gate); invoke directly only as a power user.] Generate production code and tests for a story group using agent teams for parallel execution.

• install-framework-packs

  [Internal pipeline stage — run by /scaffold; invoke directly only as a power user.] 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 manua

• keeping-refactors-pure

  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. [Internal discipline — applied automatically by pipeline agents mid-task;

• langchain-code

  Build LangChain agents in Python — create_agent, chat model initialization, tool binding, structured output, and middleware. Use for a single-agent tool-calling loop with a system prompt and a fixed tool list; use langgraph-code instead when the task needs explicit multi-step state-machine control f

• langgraph-code

  Build stateful, multi-actor LangGraph agents in Python — StateGraph definition, conditional routing, checkpointing/persistence, and human-in-the-loop interrupts. Use when a task needs explicit multi-step control flow, crash/interrupt recovery, or approval gates — not for a single-turn prompt or a si

• pe-ic-memo

  Draft a private equity investment committee memo and render it as a branded PowerPoint deck. Adapted from the installed private-equity vertical's ic-memo skill (same 9-section structure), with PPTX output instead of Word. Use when preparing IC materials, writing up a deal, or creating a formal recom

• pinning-down-behavior

  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. [Internal discipline — applied automatically by pipeline agents mid-task; direct use is a po

• portfolio-rollup

  Aggregate per-repo compliance attestations into one integrity-hashed portfolio rollup — verifying each attestation's sha256 integrity, recording an unattested repo as a compliance gap, and computing harness-version drift across the fleet. Use over a local collection directory of attestations, or wit

• pr-respond

  Respond to CI failures and review comments on a harness-opened PR — poll, classify, fix, push, reply with evidence. Bounded and budget-metered; merge stays human-owned. Use when a harness PR shows red CI or unanswered review comments.

• promote

  Implement an approved /retro recommendation and open a PR against this harness repo. Use after a human has approved a recommendation via /retro --apply-decisions. Merge always stays human — this skill only opens the PR, never merges. Refuses gate-loosen/security-class recommendations outright; those

• provision

  Provision the GitHub security-compliance gates and verify they hold. Three modes — protection (branch-protection ruleset so gitleaks+sast+code-owner review block merges), environments (deploy-approval environment so a deploy pauses for a required reviewer), fleet (retrofit BOTH gates across many rep

• react-code

  Build client-side React apps with Vite — useEffect cleanup and stale-closure bugs, dependency-array gotchas, Context vs. server-state libraries for API data, Vite environment variables, and testing with Vitest. Scoped to Vite+React client-side apps — NOT Next.js (App Router/Server Components/Server

• refactor

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

• retro

  Review this harness's own recent loop-health signals and recommend scored, evidence-backed improvements to the harness itself (skills, gates, sensors, CLAUDE.md rules) — never to product code. Use after a `/auto`/`/gate` run, on a drift cadence, or on demand when the loop feels off. Interactive-only

• reuse-or-justify

  Use when reuse-scout fires at intake (band ≥ medium, a touched constitution invariant, or a same-release clone cluster) — run the confidence-gated reuse-vs-new dialogue and record the decision + performance budget before code. [Internal discipline — invoked by /change, /feature, and /sprint intake;

• scaffold-upgrade

  Upgrade harness control-plane files (hooks, scripts, git-hooks, agents) in a previously scaffolded project without wiping project-manifest or state. Dry-run by default.

• seam-finder

  [Internal pipeline stage — run by /brownfield --seams; invoke directly only as a power user.] 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

• spec

  [Internal pipeline stage — run by /build; invoke directly only as a power user.] Decompose BRD into epics, stories, dependency graph, and feature list for agent team execution.

• sprint

  PRD-per-sprint evolution route for an existing harness-built (or brownfield) system — grounds a new PRD against the prior requirement spine, produces a human-approved design amendment against the living specs/design/ baseline, then runs /auto. Companion to /build (sprint 1) and /feature (single-stor

• sprouting-instead-of-editing

  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. [Internal discipline — applied automatically by pipeline agents mid-task; dir

• status

  Show SDLC pipeline progress — a one-shot snapshot, a live watch, or a step timeline. Read-only; aggregates the state the harness already writes. CLI-friendly (Devin-style status/watch/timeline with --json).

• tracker-publish

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

• upgrading-dependencies

  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.

• vibe

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

• writing-acceptance-tests-first

  Use when a story is about to move from acceptance criteria to implementation — in /test's plan-phase deliverable or /change Step S4, before any production code is written — to write a business-readable acceptance test against a Ports-and-Adapters seam with a test-double adapter, and confirm it fails

Slash commands (1)

• /claude_harness_eng_v5:scaffold

  Initialize a new project with the Claude Harness Engine v5 scaffold.

Subagents (10)

• advisor

  Frontier mid-run advisor. Structural re-rank / unblock / design pivot at fixed checkpoints. Read-only; never implements.

• code-reviewer

  Fresh-context review of a diff or changed-file set for both structure (SOLID breaks, duplication, god functions, hardcoded values, swallowed errors, speculative abstraction) and correctness (logic errors, missing edge cases, contract breaks). Reads only the diff and the files it touches, never the b

• codebase-explorer

  Read-only codebase exploration agent. Maps subsystems, traces dependencies, and reports findings without modifying any files. Use for brownfield discovery, architecture audits, and pre-change impact analysis.

• design-critic

  GAN counterpart for frontend quality. Takes screenshots and scores against 4 criteria (design quality, originality, craft, functionality).

• evaluator

  Skeptical verifier. Runtime mode runs the app and checks sprint-contract criteria (API + Playwright + schema). Artifact mode scores planning documents (BRD, spec, design, brownfield, seam-finder, deploy) against a rubric. Never generates — only evaluates.

• generator

  Implements code and tests from user stories. Spawns agent teams for parallel execution. Negotiates sprint contracts with evaluator.

• implementer

  Implementation worker for a SINGLE story, spawned by the generator (lead) as a team-mode teammate. Use as the subagent_type when the generator fans out one teammate per story: it implements test-first under strict file ownership and returns the result to the lead. It never spawns its own teammates a

• modularity-reviewer

  Inferential modularity review grounded in the deterministic coupling data. Reads specs/brownfield/modularity-pack.md (hubs, cycles, duplication candidates) and judges each against the source — semantic duplication, misplaced responsibility, argument clumps, and whether a high-fan-in module is a real

• planner

  Expands user prompts into BRD, decomposes into stories with dependency graph, designs system architecture, generates feature list and machine-readable schemas.

• security-reviewer

  Scans for injection, auth bypass, hardcoded secrets, SSRF, path traversal, and other OWASP top 10 vulnerabilities. Reviews only the changed-file set of a diff — the review context pack, the touched files, and their immediate data-flow neighbors — never Grepping across all source files. Complements c