Borrowing it
Nothing to install: this file belongs to T8mars/T8-penguin-canvas. 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/T8mars/T8-penguin-canvas/main/AGENTS.mdgit clone --depth 1 https://github.com/T8mars/T8-penguin-canvasWrote 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/t8mars/t8-penguin-canvas/agents-md)<a href="https://agentmods.dev/instructions/t8mars/t8-penguin-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/t8mars/t8-penguin-canvas/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/t8mars/t8-penguin-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/t8mars/t8-penguin-canvas/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 | $0.01881 | $0.01881 |
| Opus 5.5 | $0.00752 | $0.00752 |
| Sonnet 5.5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
T8-penguin-canvas 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 1mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
T8-penguin-canvas 工作约束
在修改代码、架构、配置、测试、UI、部署、GitHub 或技术文档前，以及上下文压缩后，先完整阅读本文件、根 SKILL.md、docs/project-context-current.md，再读取 package.json 的相关配置和本任务源码/测试。项目没有 meta.json。
features.json 和 roadmap.md 保持兼容完整内容，默认按任务查询，不整份加载：使用 node scripts/read-project-context.cjs find <关键词>、feature <顶层键> [子字段.路径]、manual <章节行>、roadmap <关键词>、roadmap-section <章节行>。分页未完时继续读完相关规则；旧手册完整保存在 local-private/context-archive/20260912/SKILL.md，历史授权和危险回滚示例不得覆盖当前保护规则。
记录遵守 SKILL.md 开头的精简预算：只更新当前状态与证据链接，详细过程进入专题；禁止在 SKILL/features/roadmap 多处复制长段流水账。当前任务与状态以 docs/project-context-current.md 及其指向的专题为准。
当前权威开发路径
- 用户已明确决定恢复简单工作流：
E:\PenguinPravite\T8-penguin-canvas是唯一默认开发目录。实际分支与 HEAD 每次通过 worktree 门核对，最近快照见当前上下文；下方codex/vibex-workbench-node属历史集成记录。后续代码修改、开发运行、测试与本地提交都直接在这里进行。 - merge commit 的第一父提交是 core checkpoint
4e3061094014b5dc2720d52ed178a62e8469a9d3，第二父提交是 release/F2 checkpointe0c6679b5a22539dd5b4983165ecc3f9d5c790e1。 E:\PenguinPravite\T8-penguin-canvas的codex/vibex-workbench-node已无损采用双父语义 merge commit68b5f72526a7272cc9787f6fda8b27a6f2fb54c8及后续修复；F2 与 core 的代码已经统一。E:\PenguinPravite\T8-penguin-canvas-dev-integration-f2-core-20260720只保留为已完成集成的历史参考，不再作为必需开发入口，也不要在两个目录同时修改同一功能。E:\PenguinPravite\T8-penguin-canvas-release-2.5.7继续冻结，不得在任何 release 命名路径开发。- release/F2 的旧
T8_ALLOW_LEGACY_F2_WORKTREE=1例外已随 HEAD 从9b6f6a4...移动到 checkpoint 而永久失效；这只用于继续阻止在旧 release 目录开发，不限制 canonical core。 - canonical core 的
npm run worktree:core与npm run worktree:development都必须通过；T8-penguin-canvas-dev-*仍可在特殊隔离任务中使用，但不是默认要求。release 路径必须拒绝 development。
永久保护
- 禁止
reset、clean、checkout 覆盖、整树复制、整树 ours/theirs 或任何丢弃本地修改的操作。 - 不得编辑或暂存源/core 工作树中的
tools/ffmpeg-runtime/ffmpeg.exe（143,314,432 bytes，SHA-256754A10CE2FC4A8C974FF492B351F58C02D35124D1D602FCF30F561FB1BD0F579）。 - 不得编辑或暂存源/core 工作树中的
tools/remove-ai-watermarks-runtime/README.md（2,298 bytes，SHA-25604F13F0ADBB8593372FB9DDFA297A0DFB90D9EAD0325DE0CD340FCFE8B7CED56）。 - 不得读取 retained/historical 项目数据库；数据库测试只能创建在系统临时目录并在测试后清理。
- 用户明确要求的日常开发可在 core 内修改、测试并按精确文件范围提交；版本升级、生产 build/打包、推送、tag 和 GitHub Release 仍须单独明确授权。未来正式包只构建一次。
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.
- 1mo ago Changed · +4 lines · +229 tokens per session 143e4217c209
- 1mo ago First seen · 49 lines · 1,652 tokens per session scan A 11cabbe08f38
T8-penguin-canvas AGENTS.md is an instructions file published in the GitHub repository T8mars/T8-penguin-canvas (633 stars, last pushed yesterday), licensed MIT. It adds 1,881 tokens to every session, about $0.0075 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.