ruvnet/metaharness

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

624Stars on the repository
21Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

compare-harnesses

01

ruvnet/metaharness

Skill Claude CodeCodex

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

624 +1 2d ago A 66 tokens original MIT

create-harness

02

ruvnet/metaharness

Skill Claude CodeCodex

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…

624 +1 2d ago A 89 tokens original MIT

diag-harness

03

ruvnet/metaharness

Skill Claude CodeCodex

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

624 +1 2d ago A 85 tokens original MIT

example-harness

04

ruvnet/metaharness

Skill Claude CodeCodex

Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…

624 +1 2d ago A 90 tokens original MIT

harness-secrets

05

ruvnet/metaharness

Skill Claude CodeCodex

GCP Secret Manager integration: validate setup, fetch values, or confirm an NPMTOKEN is non-revoked via npm whoami. Used for publish-time token rotation without long-lived keys in CI.

624 +1 2d ago A 47 tokens original MIT

list-templates

06

ruvnet/metaharness

Skill Claude CodeCodex

List the available harness templates and what each one ships with. Use when the user asks "what templates are available", "what verticals does the harness generator support", or "show me what I can scaffold".

624 +1 2d ago A 46 tokens original MIT

oia-manifest

07

ruvnet/metaharness

Skill Claude CodeCodex

Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.

624 +1 2d ago A 79 tokens original MIT

publish-harness

08

ruvnet/metaharness

Skill Claude CodeCodex

Publish a generated harness to npm — runs the smoke test, signs the witness manifest, and dispatches npm publish --provenance from your tagged release.

624 +1 2d ago A 37 tokens original MIT

repo-genome

09

ruvnet/metaharness

Skill Claude CodeCodex

7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.

624 +1 2d ago A 73 tokens original MIT

score-harness

10

ruvnet/metaharness

Skill Claude CodeCodex

5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.

624 +1 2d ago A 93 tokens original MIT

threat-model

11

ruvnet/metaharness

Skill Claude CodeCodex

MCP threat-model artifact for a scaffolded harness. Reports allowed/denied tools, dangerous permissions count, secrets reachability, network/shell/file-write grants, default-deny posture. Verdict: clean (exit 0) / medium (exit 1) / high (exit 2). The 'enterprise gold' artifact for PR + compliance review.

624 +1 2d ago A 76 tokens original MIT

upgrade-harness

12

ruvnet/metaharness

Skill Claude CodeCodex

Drift detection + apply for a scaffolded harness. Re-renders the template with the same vars, computes added/removed/changed file plan, and applies with Git-style conflict markers or .rej files. Default is dry-run.

624 +1 2d ago A 51 tokens original MIT

validate-harness

13

ruvnet/metaharness

Skill Claude CodeCodex

Release-readiness umbrella check for a scaffolded harness — runs doctor, witness verify, hardcoded-path scan, MCP server config, and GCP Secret Manager validation in one shot. Exits non-zero if any sub-check fails.

624 +1 2d ago A 50 tokens original MIT

verify-witness

14

ruvnet/metaharness

Skill Claude CodeCodex

Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.

624 +1 2d ago A 45 tokens original MIT

evolve

15

ruvnet/metaharness

Skill Claude CodeCodex

Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).

624 +1 2d ago A 26 tokens original MIT

plan-change

16

ruvnet/metaharness

Skill Claude CodeCodex

Turn a feature request into a minimal, file-level implementation plan before any code.

624 +1 2d ago A 19 tokens original MIT