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/studyzy/tapd-ai-cli/agents-mdgit clone --depth 1 https://github.com/studyzy/tapd-ai-cliWhat 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 | $0.01859 | $0.01859 |
| Opus 5 | $0.00929 | $0.00929 |
| Sonnet 5 | $0.00372 | $0.00372 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
tapd-ai-cli AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件为 AI 编码助手在此仓库中工作时提供指导。
项目简介
tapd-ai-cli 是一个 Go CLI 工具，通过 TAPD（腾讯敏捷产品研发平台）Open API 与 TAPD 平台交互。目标用户是 AI Agent（Claude Code、GPT-4o 等），而非人类用户。所有输出均针对最小 token 消耗进行优化。
技术栈
- Go 1.24+，CLI 框架：
spf13/cobra - SDK：
github.com/studyzy/tapd-sdk-go（独立仓库，仅依赖标准库） - HTML→Markdown：
github.com/JohannesKaufmann/html-to-markdown/v2（CLI 层，SDK 返回原始 HTML） - Markdown→HTML：
github.com/gomarkdown/markdown（create/update 时将用户输入转为 TAPD 所需的 HTML） - 认证：
TAPD_ACCESS_TOKEN（Bearer，推荐）或TAPD_API_USER/TAPD_API_PASSWORD（Basic Auth） - 许可证：Apache 2.0
构建与开发命令
# 构建（版本号从 git tag 注入）
make build # go build -ldflags "-X ...Version=$(git describe)" -o tapd ./cmd/tapd/
make build-cross # 交叉编译，需设 GOOS/GOARCH
# 安装到 $GOPATH/bin
make install
# 测试
make test # go test -race ./...
go test ./internal/cmd -run TestStoryList # 运行单个测试
make test-integration # go test ./... -v -run "TestIntegration" -count=1
# 覆盖率（目标 >= 60%）
make coverage # test-coverage + go tool cover -func
# 代码格式化与检查
make fmt # gofmt -w . && goimports -w .
make lint # go vet ./... && goimports -l .
# 安装开发工具
make tools # go install goimports
# 清理
make clean
架构
目录结构
cmd/tapd/ # 入口 main.go
internal/
cmd/ # Cobra 命令定义（每个资源一个文件），消费 SDK
root.go # 根命令、全局标志、客户端初始化、通用 helpers
story.go # 需求 CRUD 命令（典型命令模板）
bug.go # 缺陷管理
task.go # 任务管理
launch.go # 发布评审
help.go # --help 输出紧凑参考卡生成逻辑
markdown.go # htmlToMarkdown / markdownToHTML 双向转换
id_expand.go # 短 ID → TAPD 长 ID 自动展开
url.go # 从 TAPD URL 解析条目类型并查询详情
...
config/ # 凭据管理（CLI flags > env > ./.tapd.json > ~/.tapd.json）
output/ # JSON/Markdown 输出格式化、退出码常量
SDK 独立仓库：github.com/studyzy/tapd-sdk-go，本地联调可用 go.work（已 gitignore）。
命令树
tapd
├── auth login
├── workspace list | switch <id> | info
├── story list | show <id> | create | update <id> | count | todo
├── task list | show <id> | create | update <id> | count | todo
├── bug list | show <id> | create | update <id> | count | todo
├── wiki list | show <id> | create | update
├── iteration list | create | update | count
├── comment list | add | update | count
├── tcase list | create | batch-create
├── timesheet list | add | update
├── launch list | count | create | update <id> | templates | fields | logs
├── workflow transitions | status-map | last-steps
├── relation bugs | create
├── url <tapd-url>
├── skill init
└── ... release, attachment, category, custom-field, label, module, user, report 等
全局标志：--workspace-id <id>, --json, --pretty, --no-comments
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.
- 2d ago First seen · 156 lines · 1,859 tokens per session scan A a558642eb516
tapd-ai-cli AGENTS.md is an instructions file published in the GitHub repository studyzy/tapd-ai-cli (54 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,859 tokens to every session, about $0.0093 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.