Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/trabian/fluxwing-skillsnpx agentmods add skills/trabian/fluxwing-skills/fluxwing-validatorWrote 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/trabian/fluxwing-skills/fluxwing-validator)<a href="https://agentmods.dev/skills/trabian/fluxwing-skills/fluxwing-validator"><img src="https://agentmods.dev/badge/skills/trabian/fluxwing-skills/fluxwing-validator/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/trabian/fluxwing-skills/fluxwing-validator"><img src="https://agentmods.dev/badge/skills/trabian/fluxwing-skills/fluxwing-validator.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 | $0.00020 | $0.01935 |
| Opus 5 | $0.00010 | $0.00967 |
| Sonnet 5 | $0.00004 | $0.00387 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade A, and why
fluxwing-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 12d 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fluxwing Validator
Validate uxscii components and screens against JSON Schema with interactive workflows.
Overview
This skill provides two modes of operation:
- Interactive Mode: User invocation with menu and minimal output
- Direct Mode: Script calls from other skills with verbose output
When to Use This Skill
User says:
- "Validate my components"
- "Check if everything is valid"
- "Run validation on my screens"
- "Validate the project"
Other skills: Call validator scripts directly (see Technical Reference below)
Interactive Validation Workflow
Step 1: Present Validation Options
Use AskUserQuestion to present menu:
What would you like to validate?
Options:
- Everything in this project - Validates all components and screens
- Just components - Validates
./fluxwing/components/*.uxm - Just screens - Validates
./fluxwing/screens/*.uxm - Let me specify a file or pattern - Custom path/glob pattern
Step 2: Check What Exists
Before running validation, check if directories exist:
# Check for components
test -d ./fluxwing/components
# Check for screens
test -d ./fluxwing/screens
If neither exists:
- Inform user: "No components or screens found. Create some first!"
- Exit cleanly
If option 4 (custom) selected:
- Ask user for the pattern/file path
- Validate it's not empty
- Proceed with user-provided pattern
Step 3: Run Validation
Based on user selection:
Option 1: Everything
# Validate components
node {SKILL_ROOT}/validate-batch.js \
"./fluxwing/components/*.uxm" \
"{SKILL_ROOT}/../fluxwing-component-creator/schemas/uxm-component.schema.json" \
--json
# Validate screens
node {SKILL_ROOT}/validate-batch.js \
"./fluxwing/screens/*.uxm" \
"{SKILL_ROOT}/../fluxwing-component-creator/schemas/uxm-component.schema.json" \
--screens \
--json
Option 2: Just components
node {SKILL_ROOT}/validate-batch.js \
"./fluxwing/components/*.uxm" \
"{SKILL_ROOT}/../fluxwing-component-creator/schemas/uxm-component.schema.json" \
--json
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.
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.
- 12d ago First seen · 355 lines · 20 tokens per session scan A ad7fd21768e8
fluxwing-validator is a skill published in the GitHub repository trabian/fluxwing-skills (18 stars, last pushed 9mo ago), licensed MIT. It adds 20 tokens to every session and 1,935 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 2026-08-30.
Other skills, from other repositories
done
End-of-session shipping gate — "prove it works, then ship it." Runs an evidence checklist (full test suite, lint/typecheck, build, and actually running the change — output quoted, never asserted), then a fresh-context two-stage review by a sub-agent that sees only the diff and the spec: spec-compliance first…
bugfix
Lightweight bug-fixing loop — reproduce → root-cause → fix test-first → verify — deliberately separate from the heavyweight feature workflow so small fixes don't drag a spec-and-plan process behind them. Demands a deterministic reproduction before any code changes, a stated root-cause hypothesis confirmed with…
swarm-qa
A four-phase quality-assurance workflow for a live product: a broad code audit, deep live testing, coordinated fixes, and final verification. It uses multiple agents, saved checkpoints, and dated reports.
js-testing
This skill should be used when the user asks to 'write tests', 'add test coverage', 'test a component', 'test an API route', 'test a hook', 'set up Vitest', 'use React Testing Library', 'mock an API', or mentions 'component testing', 'integration tests', 'vitest', 'RTL', 'msw', 'testing library'. Provides…
verification
This skill should be used before claiming any work is complete, before committing, before creating PRs, or before reporting task status. Enforces fresh verification evidence for all completion claims. Provides the verification gate methodology: run commands, read output, then report.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.