Documentation for a registry system that matches user requests to registered skills or agents, runs them, and checks their results. It describes a flow from intent detection through execution, validation, automatic fixes, and fallback handling.

Use it when implementing or documenting a skill registry, agent selection rules, execution hooks, quality checks, or fallback behaviour.

It gives developers a common structure for adding, finding, running, and validating modular agents. This reduces ad-hoc routing and makes failures easier to handle.

config — Skill for Claude Code and Codex by dungnotnull

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 dungnotnull/standalone-solar-deep-station-agent-skill --skill config

Clone the repo

git clone --depth 1 https://github.com/dungnotnull/standalone-solar-deep-station-agent-skill

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dungnotnull/standalone-solar-deep-station-agent-skill/config/github.svg)](https://agentmods.dev/skills/dungnotnull/standalone-solar-deep-station-agent-skill/config)

Your own site

<a href="https://agentmods.dev/skills/dungnotnull/standalone-solar-deep-station-agent-skill/config"><img src="https://agentmods.dev/badge/skills/dungnotnull/standalone-solar-deep-station-agent-skill/config/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dungnotnull/standalone-solar-deep-station-agent-skill/config"><img src="https://agentmods.dev/badge/skills/dungnotnull/standalone-solar-deep-station-agent-skill/config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,290 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.03290
Opus 5.5	$0.00000	$0.01316
Sonnet 5.5	$0.00000	$0.00658
Haiku 4.5	$0.00000	$0.00329

Measured 2mo ago against content hash 703f3a8ec3f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

config 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 2mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (__init__.py, agent_registry.py, hooks.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.

config/SKILL.md · 504 lines

How it starts

The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL.md — Skill Registry Documentation

Overview

The standalone-solar-deep-station skill uses a modular, registry-based architecture that enables dynamic skill resolution, chain-of-thought routing, and graceful fallback. This document explains how skills are registered, resolved, executed, and validated.

Architecture Overview

User Query
    │
    ▼
[Intent Router] → Detect Intent + Domain Tier
    │
    ▼
[Skill Registry] → Resolve Best Agent
    │
    ▼
[Agent Execution] → Pre-Hooks → Execute → Post-Hooks
    │
    ▼
[Quality Gates] → Validate → Auto-Fix → Fallback
    │
    ▼
[Output] → Result with Metadata

Skill Registration

Registration Process

Skills are registered through the SkillRegistry class:

from config.agent_registry import get_registry, BaseAgent, SkillMetadata

# Create agent metadata
metadata = SkillMetadata(
    name="sub-core-analysis",
    version="1.0.0",
    description="Design standalone solar system for remote station",
    author="standalone-solar-deep-station",
    intent_types=[IntentType.ANALYSIS, IntentType.VALIDATION],
    domain_tiers=[DomainTier.INTERMEDIATE, DomainTier.ADVANCED, DomainTier.EXPERT],
    input_schema=get_schema("CoreAnalysisInput"),
    output_schema=get_schema("CoreAnalysisOutput"),
    dependencies=["sub-evidence-collector"],
    requires_tools=["WebFetch", "Read", "Arithmetic"],
    quality_gates=["G1", "G2", "G3", "G4"],
    tags=["solar", "pv-sizing", "battery"]
)

# Register the agent
registry = get_registry()
registry.register(agent_instance)

Metadata Requirements

Every skill must provide:

Field	Type	Required	Description
`name`	string	✓	Unique skill identifier (kebab-case)
`version`	string	✓	Semantic version
`description`	string	✓	One-line summary (used in triggering)
`author`	string	✓	Author or system identifier
`intent_types`	list	✓	Supported intents (see IntentType enum)
`domain_tiers`	list	✓	Supported complexity levels
`input_schema`	dict	✓	JSON Schema draft-07 for input validation
`output_schema`	dict	✓	JSON Schema draft-07 for output validation
`dependencies`	list	✗	Skills that must run first
`requires_tools`	list	✗	Tools required for execution
`quality_gates`	list	✗	Quality gates to apply
`tags`	list	✗	Search/metadata tags

Read the full file on GitHub · 504 lines

Files

What ships with it

8 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.

2mo ago First seen · 504 lines · 0 tokens per session scan A 703f3a8ec3f0

Subscribe to this mod's changes

config is a skill published in the GitHub repository dungnotnull/standalone-solar-deep-station-agent-skill (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,290 tokens. 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 2026-08-31.

Building agents

config next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
configdungnotnull/standalone-solar-deep-station-agent-skill	Skill	6	3mo ago	MIT	A	0	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code