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 skills add adamwang99/NEUTRON-EVO-OS --skill enginegit clone --depth 1 https://github.com/adamwang99/NEUTRON-EVO-OSWrote 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/adamwang99/neutron-evo-os/engine)<a href="https://agentmods.dev/skills/adamwang99/neutron-evo-os/engine"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/engine.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 5.1 | $0.00001 | $0.00686 |
| Opus 5 | $0.00000 | $0.00343 |
| Sonnet 5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
engine scanned grade A with 0 findings 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 8d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution Logic
Purpose
The Expert Skill Router — NEUTRON EVO OS's central dispatch engine. Audits PERFORMANCE_LEDGER.md before executing any skill. Routes tasks to appropriate skills based on CI scores and availability.
Routing Protocol
Pre-Route Audit
Before any task dispatch:
- Read
PERFORMANCE_LEDGER.md - For each candidate skill, retrieve CI score
- Check dependencies are satisfied
- BLOCK if any required skill has CI < 30
CI-Gated Routing Table
| CI Score | Routing Behavior |
|---|---|
| >= 70 | Full trust — auto-route, auto-execute |
| 40-69 | Route with verbose logging |
| 30-39 | Route with explicit verification gate |
| < 30 | BLOCK — require human review before dispatch |
Skill Priority
When multiple skills match a task:
- Prefer highest CI score
- Break ties by task count (more experienced → higher priority)
- Check dependencies are satisfied
Available Skills
| Skill | Path | Type | Dependencies |
|---|---|---|---|
| context | skills/core/context/SKILL.md |
core | none |
| memory | skills/core/memory/SKILL.md |
core | none |
| workflow | skills/core/workflow/SKILL.md |
core | context, memory |
| engine | skills/core/engine/SKILL.md |
core | none |
Engine Components
expert_skill_router.py
get_ledger_entry(skill_name): Read CI from PERFORMANCE_LEDGER.mdroute_task(task, context): Return {skill, confidence, reasoning}execute_skill(skill_path, task): Execute after CI audit passesaudit(): Full system CI health check
smart_observer.py
- Watches source file changes via watchdog
- 30-second debounce: only fires Dream Cycle after work settles
- Non-blocking: runs in background thread
start_observer(root_path, callback, debounce_seconds=30)
dream_engine.py
dream_cycle(): Full Memory 2.0 cycle (archive + prune + distill)distill_log(log_path): Compress log into Cookbook summaryNOISE_THRESHOLD = 3days (files older without reference)- Archives to
/memory/archived/ - Cookbooks go to
/memory/cookbooks/
What ships with it
2 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.
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.
- 8d ago First seen · 87 lines · 1 tokens per session scan A 4aa91411325c
engine is a skill published in the GitHub repository adamwang99/NEUTRON-EVO-OS (20 stars, last pushed 4mo ago), licensed MIT. It adds 1 tokens to every session and 686 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
metago-security-audit
A security review skill based on the OWASP Top 10, a commonly used list of major web-application security risks. It checks code, dependencies, configuration, authentication, and data handling.
metago-expert-agent-lifecycle-manager
An expert role that manages an AI agent through its full lifecycle, from defining its requirements and abilities to packaging, testing, deploying, upgrading, and retiring it. It also designs how multiple agents work together.
metago-expert-industrial-interconnect-engineer
An industrial-connectivity engineering guide for linking factory equipment such as PLCs, CNC machines and sensors to software systems. It covers industrial communication protocols, digital twins, operational-technology security and compliance standards.
metago-expert-world-model-architect
A design guide for world models: systems that represent an environment, predict what may happen after actions, and help an agent plan. It covers spatial understanding, sensor data, simulation, uncertainty, robotics, and feedback-based model updates.
metago-refactor-suggest
A code-refactoring guide that finds common code problems, measures technical debt, and suggests ordered changes while aiming to keep the program’s behaviour the same.
metago-agent-smith
Agent Manufacturing & Management Officer - specializes in requirement parsing, capability design, agent assembly, and quality inspection for intelligent agent manufacturing.