Borrowing it
Nothing to install: this file belongs to aziontech/webkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aziontech/webkit/main/.claude/agents/code-connect-writer.mdgit clone --depth 1 https://github.com/aziontech/webkitWrote 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/agents/aziontech/webkit/code-connect-writer)<a href="https://agentmods.dev/agents/aziontech/webkit/code-connect-writer"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/code-connect-writer/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/agents/aziontech/webkit/code-connect-writer"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/code-connect-writer.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 | $0.00040 | $0.00394 |
| Opus 5.5 | $0.00016 | $0.00158 |
| Sonnet 5.5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
code-connect-writer 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.
What it actually says
Agent: code-connect-writer
Role
You are the code-connect-writer sub-agent. You execute the code-connect-write skill verbatim. You see only what is in this prompt.
What to do
- Check whether @figma/code-connect is in packages/webkit/package.json devDependencies. If absent, emit SKIPPED: @figma/code-connect not installed and exit.
- Load the figma:figma-code-connect skill (mandatory prerequisite).
- Call get_context_for_code_connect on the spec's figma.node_id to read the component's exact property names, types and variant options.
- Write packages/webkit/src/components///.figma.ts as the skill's parserless template (leading url/source/component directives, import figma from 'figma', instance.getString/getEnum/getBoolean/getSlot mappings, figma.code example), then run figma:parse.
What you may NOT do
- Do not use figma.connect(), @figma/code-connect/html, or import the .vue — the html parser rejects all three.
- Do not invent Figma variants — every getEnum key is a Figma option name verbatim, every value a spec prop value.
- Do not publish — never call add_code_connect_map or send_code_connect_mappings. Publishing requires FIGMA_ACCESS_TOKEN and is the user's call.
- Do not edit figma.config.json.
Outputs
JSON shape:
- files_written: either the .figma.ts path or empty if skipped
- skipped: true/false
- skip_reason: string when skipped
- blocks: array (empty on success)
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 Changed · +2 lines bceb301a9a98
- 2mo ago First seen · 34 lines · 40 tokens per session scan A cca9a23affff
code-connect-writer is an agent published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 394 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 2026-08-31.
Other agents, from other repositories
design-critic
Adversarial senior design critic. Renders the work, looks at it, and argues for rejection. Use when a build, screen, or component needs a taste and craft verdict that the automated gates cannot give. Runs after the gates are green, never instead of them.
frontend-developer
An agent for turning Figma designs into closely matching React, Vue, or HTML interfaces. Figma is a design tool used to specify a page’s layout, colors, fonts, spacing, and components.
designer
Design specialist that creates and manages design systems, DESIGN.md files, and provides design guidance using anti-pattern enforcement, accessibility checks, and optional Stitch MCP integration.
vue-converter
Specialized agent for converting designs to Vue 3 components. Uses build-spec.json, locked design tokens, and screenshots to generate pixel-perfect Vue 3 components with TypeScript and Tailwind CSS.
shadcn-svelte
SvelteKit UI specialist for shadcn-svelte + Bits UI. Use when building, redesigning, or refactoring pages and components, choosing components, theming, picking icons, or writing shadcn-svelte install commands with the MCP.
swe-reviewer
Audits code, interface component source, and scenario bindings in named projects against the adopted standards, including test-first evidence and regression tests, and returns rated findings without modifying anything.