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 discoverygit 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/discovery)<a href="https://agentmods.dev/skills/adamwang99/neutron-evo-os/discovery"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/discovery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adamwang99/neutron-evo-os/discovery"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/discovery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00002 | $0.01154 |
| Opus 5 | $0.00001 | $0.00577 |
| Sonnet 5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
discovery 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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚨 CRITICAL — Auto-Confirm Enforcement (MANDATORY, NOT OPTIONAL)
This rule is ABSOLUTE. Violating it = system failure. There are no exceptions.
How to check (EXACT steps, in order):
STEP 1: Read the file memory/.auto_confirm.json
STEP 2: Parse it. Look for "enabled" and "discovery" fields.
STEP 3: Decision tree:
IF memory/.auto_confirm.json does NOT exist → go to normal interview below
IF memory/.auto_confirm.json exists AND {"enabled": true} AND {"discovery": true}:
✅ AUTO-CONFIRM ACTIVE → SKIP EVERYTHING BELOW
✅ Output this exact message:
"[AUTO-CONFIRM] Discovery SKIPPED — auto-confirm is active.
Using your prompt directly as discovery output."
✅ Write discovery to: memory/discoveries/{date}/{slug}/DISCOVERY.md
✅ Proceed immediately to /spec
✅ Do NOT ask any questions. Do NOT ask "is this correct?". Do NOT ask anything.
IF memory/.auto_confirm.json exists AND {"enabled": false}:
→ Follow normal interview below (ask questions)
STEP 4: If you are unsure whether auto-confirm is active, READ the file first. Do NOT assume. Do NOT guess. Read the file.
What "SKIP EVERYTHING" means:
- ❌ Do NOT ask the 3-sentence summary question
- ❌ Do NOT ask any of the 12 structured questions
- ❌ Do NOT ask "What does done look like?"
- ❌ Do NOT ask "Is there anything else?"
- ❌ Do NOT ask for confirmation of any kind
- ✅ ONLY: Read user's task → Write DISCOVERY.md → Go to /spec
Discovery Interview Skill — Understand Before Building
Purpose
Before writing a single line of code, the AI must understand WHAT the user actually wants — not what they said, but what they need. This skill conducts a structured Discovery Interview to extract the implicit from the explicit.
Input Sources (used by the interview)
The AI receives:
- User's initial prompt/spec/MVP document — the raw idea
- Existing codebase (optional) — what already exists
Interview Philosophy
Two layers:
- Structured questions — forced-choice to ensure no blind spots
- Free-form clarification — user explains in their own words
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.
- 11d ago First seen · 136 lines · 2 tokens per session scan A a134752ccd83
discovery is a skill published in the GitHub repository adamwang99/NEUTRON-EVO-OS (20 stars, last pushed 4mo ago), licensed MIT. It adds 2 tokens to every session and 1,154 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-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-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-delivery-gate
A delivery checklist for software work that links each requirement to code, tests, and proof that the result looks right. It includes screenshot comparison, where a new image is checked against a reference image.
metago-expert-dcv-economist
An expert role for measuring how people, teams, or projects contribute value using a six-part scoring model. It also evaluates credit, balance, and possible contribution risks from records such as work logs and output data.
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-knowledge-crystal-curator
A Chinese-language system for managing short-term conversation notes, long-term stored knowledge, and reusable skills. It covers saving, finding, updating, and retiring this information over time.