Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/gutomec/nirvana-os-engine/harnessnpx skills add gutomec/nirvana-os-engine --skill harnessgit clone --depth 1 https://github.com/gutomec/nirvana-os-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gutomec/nirvana-os-engine/harness)<a href="https://agentmods.dev/skills/gutomec/nirvana-os-engine/harness"><img src="https://agentmods.dev/badge/skills/gutomec/nirvana-os-engine/harness.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00154 | $0.15802 |
| Opus 5 | $0.00077 | $0.07901 |
| Sonnet 5 | $0.00031 | $0.03160 |
| Haiku 4.5 | $0.00015 | $0.01580 |
Grade B, and why
harness scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
the KEY (never client input), and refuses to run as root. The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/dispatch-auditor.md 7.0 KB
- assets/octo.ansi 3.2 KB
- baselines/2026-05-12.json 5.3 KB
- baselines/golden-bridge-cases.json 4.4 KB
- baselines/golden-multilingual-probes.json 4.8 KB
- baselines/golden-negatives.json 5.0 KB
- baselines/golden-parity.json 3.7 KB
- baselines/README.md 4.8 KB
- baselines/schema.json 3.6 KB
- BUILD-NOTES.md 10 KB
- config.yaml 3.5 KB
- CONFIGURATION.md 13 KB
- FUTURE_IMPROVEMENTS.md 24 KB
- GLANCE.md 13 KB
- HARNESS_PROTOCOL_V1.md 41 KB
- lib/agentic-router.ts 24 KB runs code
- lib/amplifier.ts 5.9 KB runs code
- lib/anomaly-detector.ts 10 KB runs code
- lib/audit-miner.ts 6.7 KB runs code
- lib/audit.js 16 KB runs code
- lib/bm25.js 19 KB runs code
- lib/bootstrap.js 1.1 KB runs code
- lib/brief-proxy.ts 4.0 KB runs code
- lib/brief-scorer.ts 7.5 KB runs code
- lib/budget.js 7.0 KB runs code
- lib/business-post-gate.ts 8.3 KB runs code
- lib/capability-resolver.ts 9.6 KB runs code
- lib/cascade-runner.ts 13 KB runs code
- lib/cascade.ts 10 KB runs code
- lib/chunk-gate.ts 2.3 KB runs code
- lib/chunk-writer.ts 4.7 KB runs code
- lib/clarification-prompt.ts 5.0 KB runs code
- lib/commands.ts 17 KB runs code
- lib/context-budget.js 5.3 KB runs code
- lib/control-plane/agent-x-canary-queue.ts 34 KB runs code
- lib/control-plane/conversation-service.ts 7.9 KB runs code
- lib/control-plane/execution-runner.ts 8.0 KB runs code
- lib/control-plane/index.ts 235 B runs code
- lib/control-plane/maestro-turn.ts 38 KB runs code
- lib/control-plane/message-route-worker.ts 493 B runs code
- lib/control-plane/message-router.ts 2.2 KB runs code
- lib/control-plane/project-service.ts 5.0 KB runs code
- lib/cooldown-registry.ts 3.7 KB runs code
- lib/cost-estimator.ts 5.7 KB runs code
- lib/critique.ts 2.8 KB runs code
- lib/dag-planner.ts 5.2 KB runs code
- lib/delivery-pipeline.ts 35 KB runs code
- lib/dispatch-cascade.ts 19 KB runs code
- lib/dispatch.ts 32 KB runs code
- lib/gauntlet/agent-x-cutover.ts 27 KB runs code
- lib/gauntlet/aggregate-budget.ts 7.4 KB runs code
- lib/gauntlet/business-canary.ts 2.9 KB runs code
- lib/gauntlet/compiler.ts 4.6 KB runs code
- lib/gauntlet/controller.ts 9.8 KB runs code
- lib/gauntlet/evaluation-contract.ts 12 KB runs code
- lib/gauntlet/evaluator-adapter.ts 14 KB runs code
- lib/gauntlet/evaluator-registry.ts 1.4 KB runs code
- lib/gauntlet/evaluator-selection.ts 13 KB runs code
- lib/gauntlet/execution-options.ts 2.4 KB runs code
- lib/gauntlet/index.ts 638 B runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +47 lines b183cab38270
- yesterday Changed · +18 lines 09d395b29d06
- 5d ago First seen · 511 lines · 154 tokens per session scan B 1788143196db
harness is a skill published in the GitHub repository gutomec/nirvana-os-engine (70 stars, last pushed today), with no licence file. It adds 154 tokens to every session and 15,802 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
red-team-tribunal
Multi-agent adversarial verification system. Use when you need thorough code review, security auditing, or quality validation. Spawns three specialized agents (Skeptic, User Proxy, Optimizer) that must reach consensus before code can be approved.
meta-ads-manager
Meta Ads (Facebook & Instagram) campaign management — creating campaigns, managing budgets, audience targeting, ad creative strategy, A/B testing, and performance optimization. This skill should be used when the user asks to create, manage, analyze, or optimize Facebook or Instagram ad campaigns, or needs ad strategy…
cli-builder
Guide for building TypeScript CLIs with Bun. Use when creating command-line tools, adding subcommands to existing CLIs, or building developer tooling. Covers argument parsing, subcommand patterns, output formatting, and distribution.
ai-video-creator
AI video creation and avatar video generation — scriptwriting, AI avatar videos (HeyGen, Synthesia, D-ID, Tavus), text-to-video generation (Kling, Runway, Fal.ai), and video content strategy. This skill should be used when the user asks to create AI videos, generate avatar/talking head videos, write video scripts…
ghostwriter
Autonomous AI ghostwriter that transforms author transcriptions and raw materials into complete, professionally formatted books. Extracts voice, identity, and method from source materials, then writes full manuscripts with proper book structure (front-matter, body, back-matter) and exports to both DOCX and PDF formats…
social-media-manager
Social media management — content creation, scheduling, cross-platform publishing, analytics, and community engagement across Instagram, Facebook, X/Twitter, LinkedIn, and TikTok. This skill should be used when the user asks to create social media posts, schedule content, plan a content calendar, analyze social…