MetaHarness integration — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150 optional-augmentation constraint
Plugin ruflo-metaharness from marketplace ruflo in ruvnet/ruflo. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
harness-benchCreate (`bench create {repo}`) or verify (`bench verify {suite.json}`) a @metaharness/darwin bench suite, the fixed corpus `harness-evolve --bench` scores variants against. Use when preparing an evolution benchmark. Degrades gracefully without darwin.
harness-drift-from-historyOne-command drift detection: run a fresh metaharness audit, diff it against the latest stored audit by ADR-152 similarity, and alert when the distance crosses `--threshold`. Use when checking whether a harness has drifted since its last audit.
harness-evolveRun `@metaharness/darwin evolve {repo}`: mutate a harness's seven policy surfaces, sandbox-score each variant and promote only measured wins. Use when evolving a harness against its tests or a bench suite. Degrades gracefully without darwin (ADR-150/153).
harness-genome7-section repo readiness report from `metaharness genome {path}`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
harness-gepaLoad, validate or render a GEPA genome, or classify failure modes in a run transcript, via @metaharness/darwin/gepa. Use when inspecting or auditing a genome; use harness-evolve for sandbox-scored evolution. Degrades gracefully without darwin.
harness-learnRun a GEPA learning cycle via `metaharness learn`, optimizing a harness genome against a SWE-bench-style slice. Use when training a harness genome. $0 dry-run by default; `--run` opts into spend. Needs a metaharness checkout (--repo or $METAHARNESS_REPO).
harness-mcp-scanStatic security scan of a harness's declared MCP surface via `harness mcp-scan {path}`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
harness-mintScaffold a custom AI agent harness via `metaharness new {name} --template {id} --host {id}`. Use when the user wants a new standalone harness. Dry-run unless --confirm is passed, and refuses to write inside the calling repo.
harness-oia-auditComposite Phase-2 audit worker (ADR-150). Bundles harness oia-manifest + threat-model + mcp-scan into one timestamped audit record stored in the `metaharness-audit` memory namespace. Designed for cron-scheduled drift detection.
harness-score5-dimension harness readiness scorecard from `metaharness score {path}` (harnessFit, compileConfidence, taskCoverage, toolSafety, memoryUsefulness, plus cost per run). Use when rating a repo as an agent harness. Pure-read; degrades gracefully without MetaHarness.
harness-security-benchRun `@metaharness/darwin security bench` (Darwin Shield): evolve a security-detection harness on a 10-vuln/9-decoy corpus and grade TPR/FPR/patch/repro against four baselines. Use when benchmarking security-harness detection. Degrades gracefully without darwin.
harness-similarityWeighted similarity (ADR-152) between two harness fingerprints (genome + score JSON): an overall score in [0,1] plus per-component breakdown. Use when comparing two harnesses or detecting drift between them. Pure TypeScript; needs no @metaharness package.
harness-threat-modelEnterprise-review-grade threat model from `harness threat-model {path}`. Categorizes MCP-surface threats; emits `worst: 'clean'|'low'|'medium'|'high'` + per-threat findings. Pure-read.
/ruflo-metaharness:ruflo-metaharnessMetaHarness integration — score, genome, mint, mcp-scan, threat-model — via subprocess invocations honoring ADR-150 architectural constraint
metaharness-architectMetaHarness integration architect for ruflo. Surfaces score/genome/mint/mcp-scan/threat-model upstream capabilities via skills; enforces ADR-150 architectural constraint (MetaHarness as removable augmentation, never required runtime dep); coordinates Phase 1 MVP rollout
node -e "require(require('path').join(process.env.CLAUDE_PLUGIN_ROOT,'scripts','_secret-env.cjs')).bridge({openrouterApiKey:'OPENROUTER_API_KEY'})"
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Agent runtimes — local WASM-sandboxed agents (rvagent) + Anthropic Claude Managed Agents (cloud); one interface, local-vs-cloud backends
5 skills · 2 commands · 9 agents
Visual workflow automation with templates, orchestration, and lifecycle management
5 skills · 8 commands · 3 agents
Neural trading strategies — self-learning LSTM/Transformer/N-BEATS models with Rust/NAPI backtesting
9 skills · 1 command · 4 agents
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Harness Adobe's creative AI-powered tools to edit images, automate design workflows, and bring creative visions to life — from background removal to vectorization and professional retouching.
26 skills · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).
6 skills · 8 commands · 4 agents · hooks
Direct CDP browser control for agents: coordinate clicks, screenshots, persistent Python session, local Chrome or Browser Use cloud. Ships skills only; the `browser-harness` CLI is a one-time install prerequisite.
3 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.