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 skills add DongLiStudio/personal-agent-foundation --skill feishu-taskgit clone --depth 1 https://github.com/DongLiStudio/personal-agent-foundationWrote 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/skills/donglistudio/personal-agent-foundation/feishu-task)<a href="https://agentmods.dev/skills/donglistudio/personal-agent-foundation/feishu-task"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/feishu-task/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/skills/donglistudio/personal-agent-foundation/feishu-task"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/feishu-task.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 | $0.00193 | $0.04362 |
| Opus 5 | $0.00097 | $0.02181 |
| Sonnet 5 | $0.00039 | $0.00872 |
| Haiku 4.5 | $0.00019 | $0.00436 |
Grade A, and why
feishu-task 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书任务
固定依赖
- 执行业务命令前先确认
lark-cli可用:优先用当前 shell 的命令发现机制,例如Get-Command lark-cli;Windows 下如命令不在 PATH,可按当前 npm 全局前缀或%APPDATA%\npm等用户级 shim 机制定位lark-cli.cmd/lark-cli.ps1,不要硬编码单一用户名路径。仍不可用时,转feishu-profile做 CLI 安装、Profile 或 workspace 恢复,不直接进入任务业务调用。 - 优先通过
lark-cli skills read lark-task读取当前 CLI 内嵌、版本匹配的任务规则;读取操作引用时使用lark-cli skills read lark-task references/<文件>。当前 CLI 不支持内嵌读取时,才使用已安装且版本匹配的 Skill 副本。 - 使用
lark-task执行搜索、创建、更新、成员、关注人、附件和回读;使用全局feishu-profile处理认证、Profile、user identity、换机恢复与配置冲突,并按需读取 CLI 内嵌lark-shared规则。 - 涉及姓名解析时使用
lark-contact,不得猜测人员open_id。 - 截图附件需要局部脱敏时使用
imagegen或当前可用的等效图像编辑能力;完成后必须回查,不能把编辑成功等同于脱敏合格。 - 按实际操作读取 create、update、search、followers、attachment 等引用;设置开始时间前必须确认当前 CLI 内嵌
lark-task对start的真实支持与语法。 - 创建或更新 start 时以当前 CLI 的
skills read、schema和命令--help为准;若 shortcut 没有 start flag,则按当前 schema 使用原生task tasks create --data .../task tasks patch --data ...或等价 JSON payload。更新 start 时必须按当前 schema 把start纳入更新字段。 - 任务写入后的排程影响判断使用
personal-schedule-planner的 飞书任务排程联动契约 和scripts/task_schedule_handoff.py;通过当前已安装 Skill 入口解析脚本位置,不硬编码用户目录。
选择飞书账号与身份
每次执行按以下优先级解析 Profile,低优先级不得覆盖高优先级:
- 用户在当前请求中明确指定的账号、公司或 Profile。
- 当前项目中与目标主体或资源直接匹配的条件化路由。
- 当前项目
AGENTS.md、项目专属 Skill 或项目长期规则明确指定的项目默认 Profile。 GLOBAL/LARK_PROFILES.md记录的全局默认 Profile。
“当前一句话未提账号”不等于“项目或 GLOBAL 未指定账号”。先检查项目条件化路由和默认规则,再继承 GLOBAL 默认。确定 Profile 后立即通过 auth status 获取实际 Profile、身份类型、当前用户姓名和 open_id,并在本次任务的全部命令中保持同一 Profile 和 user identity。
- 项目或用户明确指定 Profile 时,所有命令显式传入
--profile <Profile> --as user。 - 使用 GLOBAL 默认 Profile 时,从
GLOBAL/LARK_PROFILES.md读取治理层默认值,后续命令显式固定该 Profile;CLI active 只用于核验和发现冲突,不得覆盖 GLOBAL 默认。 - 若运行环境注入的临时配置、工作区绑定、环境变量或 CLI active/default 运行值覆盖项目或 GLOBAL 已解析的 Profile/身份,将其视为身份配置冲突。仅在当前命令进程中隔离冲突来源,再重新显式指定已解析的 Profile 和
--as user。 - 不修改全局 active Profile、全局配置或其他项目绑定,不绑定其他主体,不暴露凭据,不静默切换公司,不回退到 bot 身份。
- 指定 Profile 不存在、默认 Profile 无效、登录用户不明或 user 授权不足时,在读取敏感数据或写入任务前转交全局
feishu-profile检查和恢复;仅在主体不明或多个高优先级来源冲突时询问用户。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 146 lines · 193 tokens per session scan A 740f5a940666
feishu-task is a skill published in the GitHub repository DongLiStudio/personal-agent-foundation (11 stars, last pushed 22d ago), licensed Apache-2.0. It adds 193 tokens to every session and 4,362 once invoked, about $0.0010 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 skills, from other repositories
harness
Use when governing a workspace's control plane, code or not — the 01-TOOLS/ tooling layer, the 02-DOCS/ chaos→knowledge wiki, the root Knowledge map. Audits it, migrates legacy XX- folders, scaffolds provider tooling, sweeps the inbox, writes root CLAUDE.md/AGENTS.md. NOT the bootstrap front door (that is init, which…
swarmauri-add-standards-standalone
Add a first-class standalone Swarmauri package under pkgs/standards. Use when Codex needs package scaffolding, workspace membership, pyproject metadata, Swarmauri or Tigrbl branding, entry points, first-class citizenship registry rows, exports, tests, and validation.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…