Agent skill

At Zentao

by kairyou in kairyou/agent-tools

Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories.

MITAuto-check passedProductivity & Automation

Install At Zentao

skills CLI
$ npx skills add kairyou/agent-tools --skill at-zentao -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kairyou/agent-tools at-zentao --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kairyou/agent-tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/systems/at-zentao .claude/skills/at-zentao && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
at-zentao
GitHub stars
178
Token cost
~4k tokens
SKILL.md length
1,970 words
Files
2 (incl. scripts)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories.

  • Works in 8 steps: Fetch details — use the CLI get command.… → Restate and confirm — explain the… → Locate the code — search the current… → …
  • Referenced ZenTao items
  • SKILL.md covers Secure CLI boundary, Configuration, CLI commands and Usage, plus 4 more sections
  • Runs JavaScript scripts from its folder; calls git; needs ZENTAO_PASSWORD and ZENTAO_TOKEN

What it does

At Zentao is an agent skill from kairyou/agent-tools. Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories. Use for referenced ZenTao items, requirements, status changes, time entries, or post-implementation synchronization.

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts.

It sits in Productivity & Automation, covering Time tracking and reporting. The repository describes itself as: Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude Code, and opencode. The licence is MIT.

When your agent uses it

  • Referenced ZenTao items
  • Post-implementation synchronization

Example prompts

  • “/at-zentao”

Requirements

  • Node.js
  • A credential in ZENTAO_TOKEN

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Fetch details — use the CLI get command. Review every returned comment,
  2. Restate and confirm — explain the problem and intended fix in your own
  3. Locate the code — search the current project and explain how the relevant
  4. Fix — change only what this item requires.
  5. Verify — run the narrowest meaningful test, build, or typecheck. Reproduce
  6. Stage — first inspect git diff --staged --name-only. If unrelated files
  7. Ask whether to commit — offer Commit, Not yet, or Needs adjustment. For a
  8. Ask whether to update ZenTao — draft the exact resolution/comment and

What it can do on your machine

Read from SKILL.md and the folder at commit acc2563. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ZENTAO_PASSWORD
    • ZENTAO_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

At Zentao loads about 4k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 1,970 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from kairyou/agent-tools at commit acc2563, republished under its MIT licence (© kairyou). 1,970 words, ~3,951 tokens.

Download SKILL.mdSave it as .claude/skills/at-zentao/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
at-zentao
description
Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories. Use for referenced ZenTao items, requirements, status changes, time entries, or post-implementation synchronization.
argument-hint
bug <id> [request] | task <id> [request] | story <id> | bugs | tasks | export bug|task <id>

ZenTao Bug/Task Workflow

Secure CLI boundary

This Skill bundles scripts/zentao-cli.mjs. Resolve the Skill root as the directory containing this SKILL.md, then run the script with Node using its resolved path from any working directory:

text
node <skill-root>/scripts/zentao-cli.mjs <command>

The script is the only component allowed to read ZenTao configuration, exchange credentials for a token, send authenticated requests, or inspect raw error responses. Run it directly without reading or copying its source into the conversation. Never read ~/.agent-tools/config.jsonc, print ZenTao env vars, call the token endpoint, or construct a ZenTao Token header yourself.

The CLI emits only sanitized JSON. Treat a nonzero exit as a stopped ZenTao operation and report its safe error, message, and optional HTTP status. Do not work around the CLI with curl when authentication or an endpoint fails.

Configuration

The CLI reads the global ~/.agent-tools/config.jsonc, or $AGENT_TOOLS_HOME/config.jsonc when AGENT_TOOLS_HOME is set. It never reads repository-level configuration. Basic configuration:

jsonc
{
  "zentao": {
    "url": "https://zentao.example.com",
    "account": "user",
    "password": "your-password"
  }
}

To avoid storing the password in the file, use "password": { "env": "ZENTAO_PASSWORD" } and set that environment variable. Direct env overrides are ZENTAO_URL, ZENTAO_ACCOUNT, and ZENTAO_PASSWORD. ZENTAO_TOKEN may be used instead of password exchange; it is accepted only from the environment.

When configuration is missing, tell the user which file to edit and show the template above. Never ask them to paste a password or token into chat, and do not edit or inspect the file after they add credentials. Ask them to say "done", then validate with:

text
node <skill-root>/scripts/zentao-cli.mjs doctor

Report only whether the connection succeeded and whether authentication used token or account-password.

CLI commands

Read-only commands:

text
node <skill-root>/scripts/zentao-cli.mjs list bugs
node <skill-root>/scripts/zentao-cli.mjs list tasks
node <skill-root>/scripts/zentao-cli.mjs list stories
node <skill-root>/scripts/zentao-cli.mjs list tasks "person account or exact name"
node <skill-root>/scripts/zentao-cli.mjs list tasks "person" --relation finishedBy --status all
node <skill-root>/scripts/zentao-cli.mjs list bugs "person" --relation resolvedBy --status all
node <skill-root>/scripts/zentao-cli.mjs list stories "person account or exact name"
node <skill-root>/scripts/zentao-cli.mjs get bug <id>
node <skill-root>/scripts/zentao-cli.mjs get task <id>
node <skill-root>/scripts/zentao-cli.mjs get story <id>
node <skill-root>/scripts/zentao-cli.mjs get bug <id> --download-dir <path>
node <skill-root>/scripts/zentao-cli.mjs hours task <id>

get downloads token-gated inline images and attachments into a temporary directory by default and returns only local paths. Inspect those local files; never pass the original ZenTao URL to an image tool. For Bugs and Tasks, a configured zentao.commentPrompt is returned as writeback.commentPrompt. Use it only when drafting a write-back comment; it is not item data or an existing comment. get also returns safe comments from action history, keeping only id, actor, action, date, and non-empty comment. An omitted comments means actions were unavailable; an empty array means actions were available but contained no comments.

Write commands require JSON on stdin and are allowed only after the explicit confirmation steps below:

text
node <skill-root>/scripts/zentao-cli.mjs comment bug <id>
node <skill-root>/scripts/zentao-cli.mjs comment task <id>
node <skill-root>/scripts/zentao-cli.mjs resolve bug <id>
node <skill-root>/scripts/zentao-cli.mjs start task <id>
node <skill-root>/scripts/zentao-cli.mjs pause task <id>
node <skill-root>/scripts/zentao-cli.mjs resume task <id>
node <skill-root>/scripts/zentao-cli.mjs log-hours task <id>
node <skill-root>/scripts/zentao-cli.mjs edit-hours task <id> <effort-id>
node <skill-root>/scripts/zentao-cli.mjs finish task <id>

Input shapes:

json
{"comment":"Root cause and result."}
{"resolution":"fixed","resolvedBuild":"trunk","comment":"Root cause: stale session cache; Fix: refresh it during renewal; Commit: abc1234."}
{"realStarted":"2026-08-11 09:00:00","comment":"Started implementation."}
{"date":"2026-08-11","consumed":2,"left":14,"work":"Implemented the first part of the task."}
{"work":"Corrected work description, commit abc1234."}
{"currentConsumed":1.5,"realStarted":"2026-08-11 09:00:00","finishedDate":"2026-08-11 10:30:00","comment":"Completed: implemented session renewal; Commit: abc1234."}

For duplicate, also pass "duplicateBug": <id>. Send JSON through stdin, not as a command-line argument. The CLI handles UTF-8 form encoding and computes a task's total consumed hours from its current ZenTao value. start, pause, and resume accept an optional comment; start also accepts realStarted and otherwise uses the current time. The CLI preserves the task's current hours when starting or resuming it. log-hours defaults date to today, requires positive remaining hours, and keeps the task open. hours is read-only. edit-hours preserves omitted fields from the existing record and updates it through ZenTao's native effort workflow. Use finish when the task is complete; its comment is optional.

Usage

Read-only personnel and history queries

Interpret natural language; users do not need CLI flags. "查张三的任务" maps to list tasks "张三"; "查张三解决的 Bug" maps to list bugs "张三" --relation resolvedBy --status all; "查我完成的任务" maps to list tasks --relation finishedBy --status all. Use openedBy for created items and closedBy for items closed by the person. For all historical items still assigned to someone, use assignedTo with --status all. Completion is a relationship: finished/resolved items may have been reassigned or closed, so do not infer the finisher from assignedTo. Use an exact status only when requested (for example --status closed). Account matches take precedence over exact names. If a name is ambiguous, ask for the account. Authentication always uses the existing configuration.

These list queries are read-only. Requests to view, explain, or trace a commit also stop after reading the referenced Bug/Task, comments, and linked Story; do not enter the implementation workflow below. Extract bug/task IDs from the commit when present and use get directly. Do not infer a ZenTao account from a Git author without a matching directory entry or user clarification.

  • /at-zentao bug <id> — handle a single bug.
  • /at-zentao task <id> — handle a single task.
  • /at-zentao story <id> — read requirement scope and acceptance context. This mode is read-only; do not implement a Story status or comment workflow.
  • /at-zentao bugs — list bugs assigned to the configured account; let the user select one or more.
  • /at-zentao tasks — list assigned tasks and let the user select.
  • When the user asks to inspect another person's Bugs or Tasks, treat the named person as the query subject while keeping the configured account for authentication. Use a read-only query and state the accessible scope.
  • When the user asks for completed, closed, or historical work, include that status range only for that request. Do not expand the default actionable list.
  • /at-zentao export bug <id> or export task <id> — create a read-only, self-contained handoff bundle.

Treat text after an item id as a natural-language request. Recognize task lifecycle requests such as 开始, 暂停, 继续, start, pause, and resume, and time-entry requests such as 填工时, 记录工时, log hours, and worklog. Users do not need to know the internal CLI commands. Reuse any date, hours, or work description already supplied instead of asking twice. Recognize corrections to an existing time entry. Run hours, identify the record from returned ids and values, and ask when more than one record could match; never guess or call log-hours again to compensate for a mistake.

If a list response includes pager data showing more items than returned, tell the user the shown and total counts. Do not silently imply the list is complete. Do not browse through products/projects for the default personal list. For an explicit request about another person or historical work, use the narrowest supported read-only scope and never imply that a partial result is complete.

When a fetched Bug or Task has a positive story id, fetch that Story before planning the implementation. Use its spec and verify fields to identify scope, acceptance criteria, constraints, and non-goals. Keep the Bug or Task as the unit of work: never change, close, activate, or comment on the Story.

For a Task in wait, offer start when the user is about to work on it. For a Task in pause, offer resume; the CLI maps this to ZenTao's restart operation. Invoke pause only when the user explicitly asks or confirms that the work itself is paused; the end of a session or workday is not enough. These are status writes, so show the transition and optional comment and obtain explicit confirmation before invoking the CLI. Starting or resuming preserves the current hours and never implies new consumed time.

Show full SKILL.md (885 more words)Show less

Per-item workflow

Follow these steps in order:

  1. Fetch details — use the CLI get command. Review every returned comment, including comments attached to resolution, activation, and lifecycle actions. Read every downloaded image now so screenshots inform the fix. If no image-inspection tool is available, continue from text and state that screenshots were skipped.
  2. Restate and confirm — explain the problem and intended fix in your own words. Ask before editing when the item is ambiguous.
  3. Locate the code — search the current project and explain how the relevant code was identified.
  4. Fix — change only what this item requires.
  5. Verify — run the narrowest meaningful test, build, or typecheck. Reproduce a code-observable bug before and after when practical. For visual changes, state what was checked and what still needs the user's eyes. Stop on a failed check.
  6. Stage — first inspect git diff --staged --name-only. If unrelated files are staged, stop and ask how to handle them. Otherwise stage only files for this item by explicit path; never use git add -A.
  7. Ask whether to commit — offer Commit, Not yet, or Needs adjustment. For a commit, show a single-line Conventional Commit message before committing. Put bug#<id> or task#<id> immediately after type(scope):, for example fix(auth): bug#30887 reject expired sessions. Never commit automatically.
  8. Ask whether to update ZenTao — draft the exact resolution/comment and offer Submit, Edit first, or Comment only. Never invoke a write CLI command before confirmation. A fixed resolution must cite a real commit; without a commit, offer at most a comment with status unchanged.

Bug resolutions are fixed, notrepro, duplicate, bydesign, external, postponed, and willnotfix. Choose what matches the verified outcome. A write-back comment follows the current user request, then writeback.commentPrompt. Otherwise use the item or user's language and these defaults:

  • For a fixed Bug, use Root cause, Fix, optional Verification, and the real Commit.
  • For a finished Task, use Completed, optional Verification, and Commit only when the work has a related commit.
  • For other Bug resolutions, use Conclusion and applicable Reason or Evidence.
  • Keep standalone and lifecycle comments free-form but concise.

Formatting controls wording and layout only. Never invent missing facts; surface required gaps and put Commit: <hash> last.

Immediately before confirming any ZenTao write that cites the latest commit, run git rev-parse HEAD and git log -1 --format=%h. Do not reuse a hash from earlier conversation. If HEAD is not the item-specific commit, identify the relevant commit and tell the user instead of blindly citing HEAD.

For tasks, ask whether to record the current work after the verified result. For an incomplete task, collect the actual consumed hours and work date. When the task has a numeric current left, suggest the new left by subtracting the current entry and make that estimate editable in the confirmation; ask only when no reliable suggestion is possible. Draft work from the verified result when context is available. It is optional, so mention the omission without blocking the write when there is nothing useful to add. For a completed task, collect currentConsumed, draft the completion comment from established facts, and include both in the finish write. Never infer consumed hours or a verification result. Show all submitted values and require the same explicit ZenTao confirmation before either write.

To correct an existing time entry, use hours to select its effort id. Show the current and proposed date, consumed, left, and work, then obtain explicit confirmation and call edit-hours once. Preserve every field the user did not change. Stop when ownership cannot be verified or the edit route is unsupported. If the proposed left is zero, explicitly warn that ZenTao may change the task status as part of its native recalculation. Never edit an action comment as a substitute for correcting the underlying work-hour record, and never delete a record.

When the user wants to record hours and pause, show both exact writes in one confirmation, then run log-hours before pause. Stop if the hour write fails. Do not add lifecycle support for activate, cancel, or close.

Export mode

Export is read-only and never fixes code, commits, or writes back:

  1. Fetch the item with get, including every downloaded image/attachment.
  2. Ask where to save; default to the Desktop and never the code repository.
  3. Write a Markdown handoff with id, title, status, severity/priority, module/product, description/steps, and useful history available in the safe CLI response. Do not include credentials or login-gated URLs.
  4. With no images, write <dest>/zentao-<bug|task>-<id>.md. With images, create a same-named directory containing the Markdown and real image files, rewrite image references to relative paths, and zip only when a single artifact is needed.

Batch mode

  • Process one item at a time, each with its own stage and commit.
  • Show the pending order before starting.
  • Continue only after the current item is committed. If it remains staged, offer commit, stash and continue, or stop.
  • After each item, ask whether to continue or stop and summarize progress.

Hard rules

  • Never expose account, password, token, cookies, or authorization headers.
  • Never bypass the bundled CLI for ZenTao authentication or API access.
  • Never commit or change ZenTao state without separate explicit confirmation.
  • Keep the bug#<id> or task#<id> token in every related commit subject.
  • Collect free-form values such as output paths and hours in plain chat, not a fixed-choice prompt. Passwords and tokens are never collected in chat.

© kairyou, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/systems/at-zentao of kairyou/agent-tools.

  • SKILL.md
  • scripts/zentao-cli.mjs

Open the folder on GitHubat commit acc2563

Compare with similar skills

At Zentao next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

At Zentao compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
At Zentao this skillkairyou/agent-tools178—~4kAutomated safety check: PassMIT
Heybasecamp/hey-cli410—~20kAutomated safety check: PassMIT
Lark Todoautumnseasonism/lark-todo138—~5.5kAutomated safety check: PassMIT
Capture Triagenicepkg/ai-workflow285—~3kAutomated safety check: PassMIT
Tracking Backend WorkerCorrectRoadH/OpenTickly307—~1.2kAutomated safety check: PassAGPL-3.0
Sred Work Summarygetsentry/skills1k3 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Hey

    basecamp/hey-cli

    Interact with HEY via the HEY CLI. An agent skill from basecamp/hey-cli.

    410 GitHub stars~20k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Lark Todo

    autumnseasonism/lark-todo

    飞书全平台待办扫描:IM 消息、会议纪要、日程、文档评论、待办审批、我发起的审批、邮件、已有任务八源并行采集,按优先级排序后支持直接处理或建任务。多企业账号自动发现并并行扫描,跨企业合并。用户说'有啥待办'、'@我的消息'、'扫一圈'、'收工检查'、'今天还差啥'、'morning standup'、'daily review' 时触发,连随口'忙不忙'、'有人找我吗'也应触发。同时覆盖多企业…

    138 GitHub stars~5.5k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed
  • Capture Triage

    nicepkg/ai-workflow

    Processes Drafts Pro captures from the Inbox folder. An agent skill from nicepkg/ai-workflow.

    285 GitHub stars~3k tokensUpdated 8 mo ago
    Productivity & AutomationAuto-check passed
  • Tracking Backend Worker

    CorrectRoadH/OpenTickly

    Update backend timer/time-entry contracts, regressions, and source docs for the timer refactor mission.

    307 GitHub stars~1.2k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • Sred Work Summary

    getsentry/skills

    Official

    Go back through the previous year of work and create a Notion doc that groups relevant links into projects that can then be documented as SRED projects.

    1k GitHub starsUsed in 3 repos~1.4k tokens
    Productivity & AutomationAuto-check passed
  • Tracking Fullstack Worker

    CorrectRoadH/OpenTickly

    Implement timer/time-entry behavior that must be proven across backend truth and the browser surface together.

    307 GitHub stars~1.3k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed

More from kairyou/agent-tools

All 8 skills in this repo
  • At Review

    kairyou/agent-tools

    Review code changes for bugs, regressions, convention violations, and high-value cleanup opportunities.

    178 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • At Commit

    kairyou/agent-tools

    Generate a Conventional Commits message from staged changes and wait for confirmation before committing.

    178 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • At Vision

    kairyou/agent-tools

    Inspect screenshots, photos, diagrams, image paths, and image URLs when the task depends on visible content.

    178 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • At Daily Log

    kairyou/agent-tools

    Summarize each day's Git activity into a concise daily work log, for a single date or a range.

    178 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed
  • At Self Eval

    kairyou/agent-tools

    Summarize a contributor's Git history, a provided work log, or both into a concise, review-friendly self-evaluation for quarterly, semi-annual, or promotion cycles.

    178 GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed
  • At Simplify

    kairyou/agent-tools

    Refactor changed code to reduce duplication, complexity, and wasted work.

    178 GitHub stars~770 tokensUpdated 3 days ago
    Auto-check passed

Questions about At Zentao

What does At Zentao do?

Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories. At Zentao is an agent skill from kairyou/agent-tools. Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories.

When should I use At Zentao?

At Zentao fits situations like: referenced ZenTao items; post-implementation synchronization.

How do I install At Zentao in Claude Code?

Run `npx skills add kairyou/agent-tools --skill at-zentao -a claude-code`. Or copy the skill folder (skills/systems/at-zentao in kairyou/agent-tools) into .claude/skills/at-zentao in your project. Claude Code loads it when a task matches its description.

How do I install At Zentao in Codex?

Run `npx skills add kairyou/agent-tools --skill at-zentao -a codex`. Or copy the skill folder (skills/systems/at-zentao in kairyou/agent-tools) into .agents/skills/at-zentao in your project. Codex loads it when a task matches its description.

Can I use At Zentao in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kairyou/agent-tools --skill at-zentao -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/at-zentao, .gemini/skills/at-zentao, .github/skills/at-zentao and .opencode/skills/at-zentao in your project.

What does At Zentao need to run?

Going by SKILL.md and its folder, At Zentao needs JavaScript for the scripts in its folder, the command-line tools its instructions call (git) and credentials named ZENTAO_PASSWORD and ZENTAO_TOKEN. Our summary lists: Node.js; A credential in ZENTAO_TOKEN.

Does At Zentao access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is At Zentao safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does At Zentao use?

At Zentao is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does At Zentao use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to At Zentao?

Skills that share tags, products or a category with At Zentao: Hey (basecamp/hey-cli, 410 stars), Lark Todo (autumnseasonism/lark-todo, 138 stars), Capture Triage (nicepkg/ai-workflow, 285 stars) and Tracking Backend Worker (CorrectRoadH/OpenTickly, 307 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains At Zentao?

kairyou (a GitHub user) maintains it in kairyou/agent-tools, which has 178 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 8, 2026.

Source: kairyou/agent-tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.