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 wrap-sessiongit 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/wrap-session)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/wrap-session"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/wrap-session/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/wrap-session"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/wrap-session.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 | $0.01784 |
| Opus 5.5 | $0.00023 | $0.00714 |
| Sonnet 5.5 | $0.00012 | $0.00357 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
wrap-session 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap Session
Execute this checklist decisively, in order. Do the work - don't ask permission for each step. Only pause to ask if something is genuinely ambiguous (e.g., unsure whether a temp script is still needed).
1. Memory
Review the full session for durable facts not yet saved to memory:
- Project facts - fps, resolution, colorspace, drive layout, folder conventions, naming schemes, tool versions, decisions made
- Feedback and corrections - anything the user corrected you on, preferences they stated, approaches they rejected
- Gotchas discovered - API quirks, version incompatibilities, workarounds that took effort to find
Write or update the relevant memory files and keep the memory index current.
Explicit check: Does the active job have its loader skill (project-<job>) and is the canonical brief ...\sandbox\AGENT\PROJECT.md current with what happened this session (decisions ledger, shot ledger, open obligations, hard rules)? If not, update them now. Job facts live THERE, not in a project_<job>.md memory file - memory keeps only a one-line pointer. If the JOB itself is finishing, run /project-wrap (project-lifecycle skill) before this wrap.
2. Skills
First, flush task-observer: write any pending observations to the log
(observe.sh next-id or observe.ps1 next-id, one file each), run
observe status, and surface
the grouped summary (ids + titles, per skill) FROM THE LOG - not from memory.
They stay logged for the next review; do not apply them here unless the
review is due and Rob opts in. If nothing was logged all session, say why.
Did this session discover anything that belongs in an existing skill?
- Gotchas or workarounds relevant to a skill's domain
- API or version changes that make a skill's guidance stale
- Trigger phrases the user said that should have fired a skill but didn't - add them to that skill's description
If the edit is small, make it now. If it needs real rework, list the needed changes clearly so the user can act on them later.
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 · 126 lines · 58 tokens per session scan A ac73edf0d7ab
wrap-session 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 1,784 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
artclaw-memory
Manage ArtClaw's memory system: store/get/search/list/delete user preferences, operation history, project conventions, and user habits. Use when AI needs to: (1) remember user preferences or conventions, (2) check operation history (what was done before), (3) store lessons learned from errors, (4) maintain and compact…
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.