Borrowing it
Nothing to install: this file belongs to konbakuyomu/smartsearch. 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/konbakuyomu/smartsearch/main/AGENTS.mdgit clone --depth 1 https://github.com/konbakuyomu/smartsearchWrote 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/konbakuyomu/smartsearch/agents-md)<a href="https://agentmods.dev/instructions/konbakuyomu/smartsearch/agents-md"><img src="https://agentmods.dev/badge/instructions/konbakuyomu/smartsearch/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/konbakuyomu/smartsearch/agents-md"><img src="https://agentmods.dev/badge/instructions/konbakuyomu/smartsearch/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 | $0.00769 | $0.00769 |
| Opus 5.5 | $0.00308 | $0.00308 |
| Sonnet 5.5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
smartsearch 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 5d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- mysql_mcp_plus AGENTS.md — 100% identical, 31 lines differ
- claude-code-quickstart AGENTS.md — 100% identical, 31 lines differ
- netsuite-mcp-tools AGENTS.md — 100% identical, 31 lines differ
What it actually says
smart-search
面向 AI 与命令行用户的搜索、网页抓取和研究工具：Python 核心在 src/smart_search，npm 入口在 npm/，Windows 与 macOS 桌面 App 在 desktop/，DSH 包在 packages/。产品定位见 PRODUCT.md，桌面设计见 DESIGN.md，App 与 CLI 的边界见 docs/app-cli-boundary.md，桌面协议见 desktop/PROTOCOL.md。命令和依赖以 package.json、pyproject.toml、mise.toml 为准，发版说明在 .github/releases/。
CodeStable 与知识同步
- 入口是
/cs。小改走快改并留下ff；纯格式、错别字、依赖版本号这类改动视为"不要痕迹"，不留ff。 - 现状规格就是
codestable/spec/，不另建 ARCHITECTURE.md、GLOSSARY.md；统一语言写在codestable/spec/index.md和各子层的入口页。 - 决定（为什么这样选、否掉了什么）写
.agents/notes/，格式按 write-notes-like-deepseek，提交前跑 verify；Issue 的方案一节链接过去。codestable/notes/只放坑点和操作经验。 - 结构路径在
.arch-check.json。改了这些目录，同一次提交必须改codestable/spec/或.agents/notes/，或者在本次ff/ Issue 的「codestable」一栏写明影响；pre-commit 会检查，被拒绝时按提示补，不要绕过。 /cs的技能文件不在仓里（上游没有许可证）：会话开始时.githooks/ensure-cs.mjs按固定提交取到 .claude/skills/cs，云端自动装，本地缺了运行它加 --install。.claude/skills/README.md让这个目录随仓存在，Claude Code 才会当场发现装进来的 cs，别删。输入框不认 /cs 时运行 /reload-skills；技能列表里还没有 cs 就直接读 .claude/skills/cs/SKILL.md。- 关闭 Issue 或
ff落盘并提交成功后，在仓库目录运行board log "<一句话进展>"。云端会话经 winhand 到 Windows 的检出里运行，加 --evidence 和 PR 链接；没有 winhand 就把这句进展写进 PR 描述。
历史与边界
- 2026-10-31 起本仓试点 CodeStable-Lite 做入口，为期两周；为什么这样选、怎么验收见
.agents/notes/proposed/process/2026-10-31-codestable-lite-pilot.md。 .comet/config.yaml是以前 Comet 工作流的配置，不路由新工作。v0.1.18 删掉的带点目录.trellis/、.codestable/属于旧工作流，不要恢复；现在的codestable/（不带点）是 Lite 的。codestable/、.githooks/、.claude/settings.json、.agents/notes/只在仓里，不进 npm 包（package.json的files白名单）。
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.
- 5d ago Changed · -1 lines · +518 tokens per session b0255da42590
- 2mo ago First seen · 22 lines · 251 tokens per session scan A 6cacfe99748b
smartsearch AGENTS.md is an instructions file published in the GitHub repository konbakuyomu/smartsearch (936 stars, last pushed 5d ago), licensed MIT. It adds 769 tokens to every session, about $0.0031 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.
smartsearch AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| smartsearch AGENTS.mdkonbakuyomu/smartsearch | Instructions file | 936 | 5d ago | MIT | A | 769 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |