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 skills add jmagly/aiwg --skill cataloggit 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/catalog)<a href="https://agentmods.dev/skills/jmagly/aiwg/catalog"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/catalog/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/jmagly/aiwg/catalog"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.01012 |
| Opus 5 | $0.00012 | $0.00506 |
| Sonnet 5 | $0.00005 | $0.00202 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
catalog 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.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Catalog
You access the AIWG model catalog — listing available AI models, fetching details for a specific model, and searching by capability or name.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "which models does aiwg know about" → list
- "tell me about gpt-4o" → info
- "find models that support vision" → search vision
- "what's available for code generation" → search code generation
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| List all models | "list available models" | Run aiwg catalog list |
| Model details | "show me details for claude-3-5-sonnet" | Run aiwg catalog info claude-3-5-sonnet |
| Capability search | "what models support tool use?" | Run aiwg catalog search "tool use" |
| Name search | "search for GPT models" | Run aiwg catalog search gpt |
| Provider filter | "show Anthropic models" | Run aiwg catalog search --provider anthropic |
Behavior
When triggered:
-
Identify the subcommand:
- Is the user browsing all models, looking up a specific one, or searching by capability/name?
- Is a model ID or capability keyword mentioned?
-
Run the appropriate command:
# List all catalogued models aiwg catalog list # Show details for a specific model aiwg catalog info <model-id> # Search by capability or name aiwg catalog search <query> # Filter by provider aiwg catalog search --provider <provider-name> # Machine-readable output aiwg catalog list --json aiwg catalog info <model-id> --json -
Report the result — summarize relevant models or the requested model's details.
Examples
Example 1: List all models
User: "What models are available in the catalog?"
Extraction: List subcommand, no filter
Action:
aiwg catalog list
Response: "Catalog contains 24 models across 6 providers: Anthropic (6), OpenAI (8), Google (4), Meta (3), Mistral (2), Cohere (1). Run aiwg catalog info <id> for details on any model."
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.
- 9d ago First seen · 126 lines · 24 tokens per session scan A 86c7d165851d
catalog is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,012 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.
Other skills, from other repositories
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…
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"…
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.