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 jin-bo/agentao --skill kanban-tasksgit clone --depth 1 https://github.com/jin-bo/agentaoWrote 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/jin-bo/agentao/kanban-tasks)<a href="https://agentmods.dev/skills/jin-bo/agentao/kanban-tasks"><img src="https://agentmods.dev/badge/skills/jin-bo/agentao/kanban-tasks/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/jin-bo/agentao/kanban-tasks"><img src="https://agentmods.dev/badge/skills/jin-bo/agentao/kanban-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 236 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 330 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 317 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 355 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 497 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 199 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 296 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 341 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 492 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00221 | $0.06572 |
| Opus 5 | $0.00111 | $0.03286 |
| Sonnet 5 | $0.00044 | $0.01314 |
| Haiku 4.5 | $0.00022 | $0.00657 |
Grade A, and why
kanban-tasks scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS "$URL" >/dev/null 2>&1 && break How it starts
The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kanban 任务管理 · 操作指南
底层是本仓库虚拟环境中以 editable 模式安装的 agentao-kanban（console scripts: kanban, kanban-mcp）。
所有命令必须用 uv run kanban …，不要直接 python -m kanban，也不要 pip install。
心智模型（先看这里再动手）
- 状态机：卡片在
INBOX → READY → DOING → REVIEW → DONE中流转，外加旁路状态BLOCKED。 唯一合法的状态写入者是 orchestrator；CLI 的move是给人/Claude 用的运营手段。 - 板的位置：
kanban init会在当前目录创建.kanban/（项目根标记）和workspace/board/（卡片 与事件文件）。从该目录或任意子目录运行kanban …都能自动找回这块板，不要带--board。 - 执行器：默认
mock（离线状态机，CI 安全），加--executor agentao才会真正调用四个角色 sub-agent。除非用户明确要求"真跑"，默认保持 mock。 - 写锁：所有写命令尊重
.daemon.lock。daemon 跑着的时候不要再用--force写卡（仅应急）。 - 工作区铁律：板一旦由
kanban init落到workspace/board/，就不要把卡片相关材料散落到仓库根； 生成的笔记/数据按AGENTAO.md §Workspace入workspace/docs/、workspace/data/等。
前置自检（开工前一次）
uv run kanban --help >/dev/null # 确认 CLI 可用
uv run kanban doctor # 板 + 环境体检（无板时会提示先 init）
如果 doctor 报 stale lock / 缺失目录，运行 uv run kanban doctor --fix。
工作流
Step 1 — 把用户的需求拆成原子卡片
在动 CLI 之前，先在对话中用一个简短表格列出你打算建的卡，让用户确认或调整：
| # | title | goal | priority | depends_on | acceptance(关键 1-3 条) |
|---|
拆卡原则（按本项目 AGENTAO.md 的 Code Review 思路：Survey → Classify → Prescribe → Verify）：
- 原子性：一张卡 = 一个可独立完成、可独立验证的产出。"重构 X 模块"不是卡，"把 X.foo 拆成两个 纯函数并迁移调用点"才是卡。
- 依赖显式化：只有真依赖（B 必须等 A 的产出）才用
--depends。同主题不等于依赖。 - acceptance 是验收凭据：每张卡至少 1 条
acceptance，写成可被人/CI 直接判定通过/失败的语句 （"uv run pytest tests/foo全绿"、"workspace/reports/x.md存在且包含章节 …"）。 - 优先级保守用：默认
MEDIUM。CRITICAL仅留给阻断其他卡或线上故障类。
Step 2 — 初始化（仅当 .kanban/ 不存在）
uv run kanban init # 干净起步：建 .kanban/ + workspace/board/
# 或带示例卡先看效果：
uv run kanban init --demo
如果用户说"先看看 kanban 怎么跑"，跑：
uv run kanban init --demo
uv run kanban demo # 把 4 张示例卡推到 DONE
uv run kanban list
Step 3 — 建卡
每张卡用一条命令；--acceptance 与 --depends 可重复：
uv run kanban card add \
--title "把 ingest.py 拆成 reader/parser 两个纯函数" \
--goal "降低 ingest.py 圈复杂度并允许独立单测" \
--priority MEDIUM \
--acceptance "uv run pytest tests/ingest 全绿" \
--acceptance "ingest.py 中无对全局状态的读写"
What ships with it
12 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.
- playbooks/break-down-requirements.md 4.9 KB
- playbooks/cards.template.yaml 1.4 KB
- references/advanced.md 4.0 KB
- references/cli-cheatsheet.md 5.1 KB
- references/inspect.md 3.5 KB
- references/services.md 3.6 KB
- references/troubleshooting.md 3.7 KB
- scripts/kanban_cards_from_yaml.py 2.7 KB runs code
- scripts/kanban-down.sh 948 B runs code
- scripts/kanban-status.sh 722 B runs code
- scripts/kanban-up-real.sh 1.7 KB runs code
- scripts/kanban-up.sh 1.7 KB runs code
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.
- 10d ago First seen · 515 lines · 221 tokens per session scan A 6c509e90f6cc
kanban-tasks is a skill published in the GitHub repository jin-bo/agentao (300 stars, last pushed 2d ago), licensed MIT. It adds 221 tokens to every session and 6,572 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.