config-validator

config-validator is a skill for Claude Code, Codex from jmagly/aiwg. It costs 15 tokens per session (2,535 once invoked), scanned A, original, MIT.

A configuration checker for AIWG projects that validates YAML and JSON syntax, required settings, file paths, and references between configuration entries.

In plain words
What is it for?
Use it to check configuration files, missing fields, referenced files, agent references, and template paths.
Why use it?
It catches malformed, incomplete, conflicting, or broken project setup before it causes workflow failures.

Skill for Claude CodeCodex

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

Good fit Use it to check configuration files, missing fields, referenced files, agent references…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jmagly/aiwg/config-validator
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 jmagly/aiwg --skill config-validator
Clone the repo
git clone --depth 1 https://github.com/jmagly/aiwg

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 config-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmagly/aiwg/config-validator.svg)](https://agentmods.dev/skills/jmagly/aiwg/config-validator)
Your own site
<a href="https://agentmods.dev/skills/jmagly/aiwg/config-validator"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/config-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,535 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 $0.00015 $0.02535
Opus 5 $0.00008 $0.01267
Sonnet 5 $0.00003 $0.00507
Haiku 4.5 $0.00002 $0.00253

Measured 3d ago against content hash bea180491ae6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

config-validator 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 3d 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.

agentic/code/addons/aiwg-utils/skills/config-validator/SKILL.md · 510 lines

How it starts

The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.

config-validator

Validate AIWG configuration files and project setup for correctness and completeness.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "validate [YAML/JSON]" in configuration context → config schema check
  • "is this valid config" → configuration validation

Purpose

This skill ensures AIWG projects are properly configured by:

  • Validating YAML/JSON configuration syntax
  • Checking required fields and values
  • Verifying file references and paths
  • Detecting configuration conflicts
  • Recommending fixes for issues

Behavior

When triggered, this skill:

  1. Locates configuration files:

    • Scan for AIWG config files
    • Identify framework configs
    • Find project-specific configs
  2. Validates syntax:

    • Parse YAML/JSON files
    • Check for syntax errors
    • Validate structure against schema
  3. Checks completeness:

    • Verify required fields present
    • Check for missing sections
    • Validate cross-references
  4. Verifies references:

    • Check file paths exist
    • Validate agent references
    • Verify template paths
  5. Detects conflicts:

    • Duplicate definitions
    • Conflicting settings
    • Incompatible options
  6. Generates report:

    • List all issues found
    • Severity classification
    • Fix recommendations

Configuration Files Validated

AIWG Core Configs

aiwg_configs:
  project_config:
    path: .aiwg/config/project.yaml
    schema: schemas/project-config.schema.yaml
    required_fields:
      - project_name
      - project_type
      - phase

  team_profile:
    path: .aiwg/team/team-profile.yaml
    schema: schemas/team-profile.schema.yaml
    required_fields:
      - team_name
      - members

  risk_register:
    path: .aiwg/risks/risk-register.yaml
    schema: schemas/risk-register.schema.yaml
    required_fields:
      - risks

  artifact_config:
    path: .aiwg/config/artifacts.yaml
    schema: schemas/artifact-config.schema.yaml

Read the full file on GitHub · 510 lines

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. 3d ago First seen · 510 lines · 15 tokens per session scan A bea180491ae6

Subscribe to this mod's changes

config-validator is a skill published in the GitHub repository jmagly/aiwg (209 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 2,535 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

debug

Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.

Master0fFate/parallax-claudecode · 18 tokens

parallax-core

Apply session-safe Parallax reasoning and verification to code changes.

Master0fFate/parallax-claudecode · 16 tokens

typescript-circular-dependency

Detect and resolve TypeScript/JavaScript circular import dependencies. Use when: (1) "Cannot access 'X' before initialization" at runtime, (2) Import returns undefined unexpectedly, (3) "ReferenceError: Cannot access X before initialization", (4) Type errors that disappear when you change import order, (5) Jest/Vitest…

Wania-Kazmi/claude-code-autonomous-agent-workflow · 88 tokens

nextjs-server-side-error-debugging

Debug getServerSideProps and getStaticProps errors in Next.js. Use when: (1) Page shows generic error but browser console is empty, (2) API routes return 500 with no details, (3) Server-side code fails silently, (4) Error only occurs on refresh not client navigation. Check terminal/server logs instead of browser for…

Wania-Kazmi/claude-code-autonomous-agent-workflow · 87 tokens

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

affaan-m/ECC · 46 tokens

triage-issue

Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.

aden-hive/hive · 0 tokens