Borrowing it
Nothing to install: this file belongs to danielwpz/lark-a2ui-renderer. 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/danielwpz/lark-a2ui-renderer/main/AGENTS.mdgit clone --depth 1 https://github.com/danielwpz/lark-a2ui-rendererWrote 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/instructions/danielwpz/lark-a2ui-renderer/agents-md)<a href="https://agentmods.dev/instructions/danielwpz/lark-a2ui-renderer/agents-md"><img src="https://agentmods.dev/badge/instructions/danielwpz/lark-a2ui-renderer/agents-md/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/instructions/danielwpz/lark-a2ui-renderer/agents-md"><img src="https://agentmods.dev/badge/instructions/danielwpz/lark-a2ui-renderer/agents-md.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 | $0.02120 | $0.02120 |
| Opus 5.5 | $0.00848 | $0.00848 |
| Sonnet 5.5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
lark-a2ui-renderer AGENTS.md 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 2mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lark-a2ui-renderer Agent Guide
This directory is an experimental standalone TypeScript package for rendering a constrained A2UI v0.8 subset into Feishu/Lark interactive card JSON.
Project Goal
Build a reusable, application-independent renderer library:
- Accept A2UI v0.8 server messages from an LLM or host application.
- Validate the supported Lark-card catalog subset.
- Maintain A2UI surface state.
- Compile the surface into Feishu/Lark Card JSON 2.0.
- Inject callback metadata for interactive controls.
- Normalize callbacks into A2UI
userActionevents.
The package must not own application business logic, LLM calls in production, message routing, persistence, or authorization decisions.
Versioning
Follow the official A2UI renderer layout:
src/index.tsre-exports the default supported version.src/v0_8/contains the current implementation.- Future protocol versions must go into separate directories such as
src/v0_9/; do not mix protocol implementations. - Package exports include
.and./v0_8.
Current target:
- A2UI protocol: v0.8 stable.
- Catalog id:
urn:a2ui:catalog:lark-card:v0_8. - v0.9 work is intentionally out of scope for now.
- Dynamic data sources and live pixel-grid rendering are custom experimental
extensions on top of v0.8. Do not describe them as official A2UI v0.8
behavior. See
docs/dynamic-data-sources.md.
Important Local Rules
- Use this package's own TypeScript toolchain. Do not run source through another
repository's
node_modules,tsx, or test runner. - Do not commit changes unless explicitly asked.
- Do not invent Feishu/Lark raw callback payload shapes. Use official docs or capture real payloads with integration tests.
- Do not print secrets. In particular, avoid SDK logs that include request
config containing
app_secret. - Keep probing scripts out of committed source. Use
.tmp/ortest/integrationonly when the probe itself is a deliberate integration test.
Key Files
src/v0_8/types.ts: A2UI subset and renderer contract types.src/v0_8/surface.ts: Applies A2UI v0.8 messages to surface state.src/v0_8/render.ts: Compiles A2UI surfaces into Feishu/Lark Card JSON.src/v0_8/callback.ts: Extracts Feishu/Larkcard.action.triggercallbacks into normalized callback input and normalizes that into A2UIuserAction.src/v0_8/validate.ts: Renderer-specific semantic validator.catalogs/lark-card/v0_8/catalog.json: Current supported A2UI catalog subset.docs/llm-authoring.md: Instruction sheet for LLM JSON generation tests.docs/dynamic-data-sources.md: Experimental channel-neutral datasource extension design. It must stay separate from Lark-specific CardKit behavior.fixtures/: Stable semantic fixtures.skills/: Distributable agent skill for authoring and validating this A2UI subset. It must stay usable without the full source repository.scripts/sync-skill-runtime.js: Copies compiled v0.8 runtime files intoskills/runtime/v0_8for standalone skill distribution.test/support/lark-case-matrix.ts: Shared generated case matrix for offline and real Lark integration tests..env.integration.example: Template for real LLM/Lark integration settings.
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.
- 2mo ago First seen · 242 lines · 2,120 tokens per session scan A ed0adecf11fc
lark-a2ui-renderer AGENTS.md is an instructions file published in the GitHub repository danielwpz/lark-a2ui-renderer (13 stars, last pushed 5mo ago), licensed MIT. It adds 2,120 tokens to every session, about $0.0085 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.