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 agentmods add skills/jmagly/aiwg/validate-metadatanpx skills add jmagly/aiwg --skill validate-metadatagit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/validate-metadata)<a href="https://agentmods.dev/skills/jmagly/aiwg/validate-metadata"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/validate-metadata.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01253 |
| Opus 5 | $0.00013 | $0.00626 |
| Sonnet 5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
validate-metadata 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 yesterday.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Metadata
You validate all AIWG extension definitions (agents, skills, commands, behaviors) against the metadata schema. You report errors with field names, line numbers, and remediation hints — and return a clean pass/fail summary.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "are my extensions valid?" → run full metadata validation
- "check my agent definitions" → validate agent metadata specifically
- "is this skill definition correct?" → validate single extension file
- "prep for release" → validate metadata as part of pre-release checks
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Validate request | "validate metadata" | Run aiwg validate-metadata |
| Check request | "check metadata" | Run aiwg validate-metadata |
| Validate extensions | "validate extensions" | Run aiwg validate-metadata |
| Quality check | "metadata quality" | Run aiwg validate-metadata |
| Single file | "validate this agent file" | Run aiwg validate-metadata <path> |
| Directory-scoped | "validate just security skills" | Run aiwg validate-metadata --recursive agentic/code/frameworks/security-engineering/skills |
| CI mode | "validate metadata for CI" | Run aiwg validate-metadata --ci --format json --strict |
Behavior
When triggered:
-
Extract intent:
- Is validation scoped to a specific extension type (agents, skills, commands, behaviors)?
- Is a specific file path mentioned?
- Is verbose output needed?
-
Run the appropriate command:
# Default: validate all extensions aiwg validate-metadata # Recursive validation of a directory aiwg validate-metadata --recursive agentic/code/frameworks/security-engineering/skills # Strict CI output aiwg validate-metadata --ci --format json --strict # Validate a single file aiwg validate-metadata agentic/code/addons/aiwg-utils/skills/my-skill/SKILL.md
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.
- yesterday First seen · 154 lines · 26 tokens per session scan A 2c9c5ceb0e8a
validate-metadata is a skill published in the GitHub repository jmagly/aiwg (209 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,253 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 2026-09-05.
Other skills, from other repositories
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.