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 sideshowroberto/vfx-agent-toolkit --skill gap-checkgit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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/sideshowroberto/vfx-agent-toolkit/gap-check)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/gap-check"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/gap-check/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/sideshowroberto/vfx-agent-toolkit/gap-check"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/gap-check.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 | $0.00058 | $0.00642 |
| Opus 5.5 | $0.00023 | $0.00257 |
| Sonnet 5.5 | $0.00012 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
gap-check 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are about to audit your own knowledge against the current plan. The goal is to surface silent assumptions and fill gaps with research BEFORE planning or building begins.
Step 1 - State the plan
In one sentence, restate the settled scope from the current conversation so the user can confirm it's correct before proceeding.
Step 2 - Self-audit
Go through every technical component of the plan. For each, honestly categorize your knowledge:
[OK] Confident - You have seen this documented or used it correctly in verified contexts. State your source if possible.
~ Uncertain - You know the general shape but are fuzzy on specifics, version details, or edge cases. State what you're unsure about.
[FAIL] Guessing - You are inferring from related knowledge or pattern-matching. You could be wrong. State the assumption explicitly.
Be ruthless. The most common failure mode is treating ~ and [FAIL] items as [OK]. If you haven't verified it recently or it's version-sensitive, it's not [OK].
Step 3 - Classify gaps by who can fill them
After the audit, sort the ~ and [FAIL] items into three buckets:
Search-specialist can answer - Public API docs, version changelogs, GitHub issues, library behavior. Launch a search-specialist agent for each cluster of related questions. Run them in parallel where possible.
User must answer - Studio-specific preferences, internal pipeline details, decisions only the user can make. Ask these as a short list - don't guess.
Testable locally - Things that can be verified with a quick command or code snippet. Flag these for the user to test before the build session.
Step 4 - Launch research
For any items in the "search-specialist can answer" bucket, immediately dispatch search-specialist agents in parallel. Be specific in the agent prompts - include the exact version, platform, and context so results are actionable.
Step 5 - Deliver validated summary
Once research returns, deliver a clean summary:
VALIDATED KNOWLEDGE
[OK] [item] - [source or confidence reason]
[OK] [item] - [source or confidence reason]
GAPS FILLED BY RESEARCH
[OK] [item] - [what research found]
~ [item] - [what research found, still some uncertainty]
GAPS REQUIRING USER INPUT
? [question]
? [question]
GAPS TO TEST LOCALLY
[what to test] - [one-liner or command]
STILL UNKNOWN
[FAIL] [item] - [why it couldn't be resolved and what the risk is if assumed]
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.
- today First seen · 63 lines · 58 tokens per session scan A 0ee96658fabb
gap-check is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 58 tokens to every session and 642 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-02.
Other skills, from other repositories
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
mesh-ops
Cross-adapter polygon modeling recipe pack for the shared cross-DCC modeling vocabulary. Structured RECIPES.yaml entries for primitive creation, hard-surface edits, topology cleanup, UV generation, radial arraying, and material assignment. Reusable by every DCC adapter's mesh-ops skill (maya, blender, houdini, 3dsmax…
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…