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 instructions/cadeyu/vibe-harness/agents-mdgit clone --depth 1 https://github.com/CadeYu/vibe-harnessWrote 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/cadeyu/vibe-harness/agents-md)<a href="https://agentmods.dev/instructions/cadeyu/vibe-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/cadeyu/vibe-harness/agents-md.svg" alt="Measured on agentmods" 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 | $0.00552 | $0.00552 |
| Opus 5 | $0.00276 | $0.00276 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
vibe-harness 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 4d 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.
What it actually says
仓库指令
这个仓库定义 Vibe Harness：一个 repo-native 的 AI-assisted development framework。
项目规则
- 所有 artifacts 都应该能复制到普通软件项目里使用。
- 优先写具体模板，不写空泛方法论。
- 不绑定某一个 AI coding 产品。
prompts/保持短、清楚、可直接粘贴。skills/和prompts/要分工明确：prompt 是一次性指令，skill 是可复用操作规程。scripts/check.sh和scripts/verify.sh是一等公民，不是附属品。feature_list.json是范围和完成状态的一等公民，passing必须有 evidence。- 框架自身一次只推进一个 feature，避免文档、模板和脚本同时漂移。
文档风格
- 中文为主，保留英文技术锚点。
- 文件名、命令、skill name、commit message 示例保持 English。
- 解释每个 artifact 为什么存在、什么时候用。
- 避免不可执行的流程空话。
- 示例要小到能在一次阅读里理解。
安全规则
- 不把 destructive git commands 作为默认工作流。
- 不包含真实 credentials、tokens 或私有 endpoints。
- 脚本不要删除文件、重建数据库或执行不可逆操作。
- 检查脚本应该 fail loudly，并且容易按项目定制。
验证
完成前运行：
sh -n templates/base/scripts/check.sh
sh -n templates/base/scripts/verify.sh
sh -n scripts/init-harness.sh
sh -n scripts/clean-state.sh
sh -n templates/base/scripts/init-harness.sh
sh -n templates/base/scripts/clean-state.sh
sh -n scripts/validate-feature-list.sh
sh -n templates/base/scripts/validate-feature-list.sh
sh -n scripts/check-consistency.sh
sh tests/test_consistency.sh
扫描公开文档里的未完成标记：
rg -n "TB[D]|TO[D]O|FIXM[E]|placeholde[r]|coming soo[n]" README.md AGENTS.md templates prompts skills docs/*.md examples
完成标准
一个改动完成需要满足：
- 被编辑 artifact 有单一清晰职责
- 相关 docs、prompts、skills 保持一致
- shell scripts 通过语法检查
- framework loop 仍然清晰可用
- final response 给出简洁 English commit message
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.
- 4d ago First seen · 63 lines · 552 tokens per session scan A fa36c56faaaa
vibe-harness AGENTS.md is an instructions file published in the GitHub repository CadeYu/vibe-harness (5 stars, last pushed 2mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0028 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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.