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/apurvbazari/claude-plugins/rendernpx skills add ApurvBazari/claude-plugins --skill rendergit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWhat 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 | $0.00060 | $0.00528 |
| Opus 5 | $0.00030 | $0.00264 |
| Sonnet 5 | $0.00012 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
render 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.
What it actually says
Render — Assemble a Supplied Model into the House Style
You are invoked by a caller (e.g. the lens plugin) that has already synthesized a model in
context. You are the programmatic entry for the terminal render stages: skip gather + synthesize
and run only select → assemble → self-check → write. The model conforms to
../create/references/session-model.md (review fields allowed).
references/render-contract.md is the canonical description of those four shared stages (it is the
same select → assemble → self-check → write every producer ends on) plus the review-specific assembly
(findings[] → sheets, diffHunks[], adherence, verdict). Follow it for the render half.
Step 1: Locate the model + output path
The caller passes (a) a structured model in context and (b) an output path argument. If NO model is present in context, stop and tell the user: "Nothing to render — use /walkthrough:create for a session recap." Never synthesize from the transcript here.
Step 2: Run the shared render stages
Run select → assemble → self-check → write exactly as described in references/render-contract.md,
including its § Review-specific assembly for findings/diffHunks/adherence. Write to the
caller-supplied output path (create the directory if missing); do not prompt for gitignore (the caller
owns its output location). Return the written path to the caller.
Key Rules
- Internal only.
user-invocable: false; callers invoke it via the Skill tool. - No synthesis. Render the supplied model verbatim — never re-derive from the transcript.
- Follow the contract. The shared stages + review assembly live in
references/render-contract.md; this skill is their programmatic entry point, not a second copy of them. - Self-contained + tokens only. Same invariants as create; run the structural self-check before write.
- Empty context → redirect to create. Never silently fall back to synthesis.
What ships with it
1 file 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.
- yesterday First seen · 36 lines · 60 tokens per session scan A 1b6aa0a275ec
render is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 60 tokens to every session and 528 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.