Borrowing it
Nothing to install: this file belongs to taux-io/twse-mcp. 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/taux-io/twse-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/taux-io/twse-mcpWrote 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/taux-io/twse-mcp/agents-md)<a href="https://agentmods.dev/instructions/taux-io/twse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/taux-io/twse-mcp/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/taux-io/twse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/taux-io/twse-mcp/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 | $0.02075 | $0.02075 |
| Opus 5.5 | $0.00830 | $0.00830 |
| Sonnet 5.5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
twse-mcp 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 8d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
台股資料 MCP server。給任何 AI 代理讀的專案慣例；
使用說明看 README.md，詞彙定義看 CONTEXT.md，
決策與實測紀錄看 docs/spec-workers-migration.md，
架構決策看 docs/adr/——那裡有活的操作約束（例如導入認證前必須重新評估
cacheScope），不是純歷史。
更新紀錄
使用者看得到的改動，合併時寫進 CHANGELOG.md 與 CHANGELOG.en.md 的「尚未編號」一節（沒有就在最新版本上面新增）；
升版時把那一節改成版本號與日期。只寫對使用者的影響，不寫內部重構。
npm run check-readmes 會擋下 package.json 版本在兩份 CHANGELOG 裡沒有對應一節的情況。
分支保護
main 要 PR 才能合併，required check 只有 test（test.yml 的 job）。設定在 GitHub，現況用
gh api repos/taux-io/twse-mcp/branches/main/protection 查。
upstream health的 job 叫check，只在排程時跑；把它加進 required，每個 PR 都會永遠卡住。- 改
test這個 job 的名稱、或給它的pull_request觸發加paths篩選，PR 一樣會卡住。scripts/check-required-checks.mjs在 CI 擋這兩件事；改了 GitHub 上的設定要同步它的REQUIRED_CHECKS， 再跑npm run check-required-checks -- --remote對一次。
依賴升級
Dependabot 的 PR 都改 package-lock.json，合併一個後其他的會衝突：留言 @dependabot rebase，一次重建一個。
smoke 在 push 到 main 時不跑，合併後要驗就 gh workflow run smoke.yml。
驗證做法與新舊回應比對的結果見 docs/dependency-upgrade-2026-10-17.md。
Agent skills
Issue tracker
Issues 存放在 GitHub（taux-io/twse-mcp），以 gh CLI 操作。見 docs/agents/issue-tracker.md。
Triage labels
沿用五個標準標籤，字串與角色同名。見 docs/agents/triage-labels.md。
Domain docs
Single-context：根目錄一份 CONTEXT.md，ADR 放 docs/adr/。見 docs/agents/domain.md。
Ponytail checkpoints
commit 前、接手或重構前、每週或階段結束，各跑一個 ponytail 過度工程檢查。
時機、標記慣例，以及這個 repo 的防禦性守衛為什麼不算冗餘，見 docs/agents/ponytail.md。
Answer eval
npm run eval:answers 讓 Claude Code 真的查完、作答，再用規則核對答案（scripts/eval-answers.mjs）。eval:tools
只看第一個工具呼叫，看不到多步驟的後續（先查代號，再帶對參數），也看不到模型有沒有照回應裡的說明讀數字
（單位、累計數、N/A 不是 0）。改到 caveats、note、單位說明，或回應裡任何給模型讀的解說文字時，兩個模型各跑一次
（EVAL_REPEAT=3）。標準答案取自同一次對話的工具結果；每題是通過、失敗、需人工看、沒驗到四種之一——「沒驗到」
不算通過。「說它沒有」這類反向句用規則寫不完（否定、疑問、引用別家），命中只標「需人工看」，要讀原文判斷。
只打本機、需要登入的 Claude Code，所以不進 CI。
Smoke test
npm run smoke 對本機 wrangler dev（8787）的每支工具發一個真實查詢，兩代協定各一遍；8787 沒人用就自己起、跑完關掉。改到工具回應的形狀或
outputSchema 時在本機跑一次；CI（.github/workflows/smoke.yml）在每個 PR 與每天定時跑，定時的失敗會開 issue。
預設不打正式環境：它跑在 Workers 免費方案，每個請求都在消耗 CPU 的寬容額度（#104）。
例外是每天排程裡的正式環境存活檢查（SMOKE_LIST_ONLY=1）：只看工具清單、快捷指令與首頁，不呼叫工具。
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.
- 8d ago Changed · +5 lines · +100 tokens per session 3afaf465a558
- 11d ago Changed · +3 lines · +68 tokens per session 6977e5089cb2
- 13d ago Changed · +13 lines · +248 tokens per session 740e3e54a844
- 1mo ago Changed · +27 lines · +694 tokens per session 411584d582ef
- 1mo ago Changed · +29 lines · +723 tokens per session 6a380dbc374f
- 2mo ago First seen · 22 lines · 242 tokens per session scan A 6a1d26727ba7
twse-mcp AGENTS.md is an instructions file published in the GitHub repository taux-io/twse-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 2,075 tokens to every session, about $0.0083 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 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.