workflow

workflow is a skill for Claude Code, Codex from adamwang99/NEUTRON-EVO-OS. It costs 1 tokens per session (2,347 once invoked), scanned A, original, MIT.

A project workflow that guides coding work through exploration, user questions, a written specification, building, and user testing. It also checks whether automatic confirmations are enabled before starting.

In plain words
What is it for?
Use it to take a non-trivial project from an initial idea through research, specification, implementation, and acceptance testing.
Why use it?
It reduces unclear requirements and keeps major decisions visible before code is written. The required review and testing steps help catch misunderstandings earlier.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to take a non-trivial project from an initial idea through research, specification, implementation, and acceptance testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adamwang99/neutron-evo-os/workflow
Install

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.

Any agent
npx skills add adamwang99/NEUTRON-EVO-OS --skill workflow
Clone the repo
git clone --depth 1 https://github.com/adamwang99/NEUTRON-EVO-OS

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/workflow/github.svg)](https://agentmods.dev/skills/adamwang99/neutron-evo-os/workflow)
Your own site
<a href="https://agentmods.dev/skills/adamwang99/neutron-evo-os/workflow"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/workflow/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.

agentmods 80×15 button for workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/adamwang99/neutron-evo-os/workflow"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00001 $0.02347
Opus 5 $0.00000 $0.01174
Sonnet 5 $0.00000 $0.00469
Haiku 4.5 $0.00000 $0.00235

Measured 9d ago against content hash b6d194670814, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workflow 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (logic/__init__.py, validation/__init__.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/core/workflow/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚡ FIRST STEP: Check Auto-Confirm Status

BEFORE doing anything else, check if auto-confirm is enabled:

1. Read memory/.auto_confirm.json
2. If {"enabled": true}:
   - discovery=true  → Skip /discovery, use task description directly
   - spec=true       → After writing SPEC.md → AUTO-APPROVE, proceed to /build
   - acceptance=true → After /build → AUTO-PASS, proceed to /ship
   - ONLY /ship rating is always requested from the user
3. If {"enabled": false} or file missing → Follow normal gates below

This is mandatory — every workflow step starts by checking auto-confirm.


Execution Logic — NEUTRON EVO OS Workflow v2.0

Purpose

Execute the structured project delivery workflow with human-in-the-loop gates. Every non-trivial project goes through ALL 5 steps. No skipping.


The 5-Step Pipeline

USER IDEA
    ↓
/explore     → Understand problem space, check system health
    ↓
/discovery    → Structured interview: AI asks 12 clarifying questions
    ↓
/spec        → Write SPEC.md → USER REVIEW (HARD GATE — must approve before build)
    ↓
/build       → Implement exactly what SPEC says
    ↓
/acceptance_test  → USER runs the app, verifies it solves their problem
    ↓
/ship        → Deliver, archive, update rating
    ↓
ITERATE (if acceptance failed) or DONE

Key Principle: USER REVIEW Gate

The AI NEVER builds without the user's explicit approval of the SPEC. This is the single most important gate in the entire workflow. Build = user has approved SPEC. No approval = no build.


Step 1: /explore

Goal: Verify system health and understand the problem space.

Actions:

  1. Read SOUL.md, MANIFESTO.md (identity check)
  2. Audit PERFORMANCE_LEDGER.md — block if any required skill CI < 30
  3. Audit memory/ — find relevant prior decisions
  4. Read existing codebase (if project exists)
  5. Draft a 1-paragraph problem statement

Exit gate: Problem statement written. System ready.


Step 2: /discovery

Read the full file on GitHub · 277 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 277 lines · 1 tokens per session scan A b6d194670814

Subscribe to this mod's changes

workflow 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 2,347 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.

Related

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-ai/metagolifeform · 75 tokens

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-ai/metagolifeform · 81 tokens

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-ai/metagolifeform · 67 tokens

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-ai/metagolifeform · 84 tokens

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-ai/metagolifeform · 69 tokens

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.

metago-ai/metagolifeform · 80 tokens