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 commands/bladeofgod/flutter-ai-harness/plan-tasksgit clone --depth 1 https://github.com/bladeofgod/flutter-ai-harnessWrote 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/commands/bladeofgod/flutter-ai-harness/plan-tasks)<a href="https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/plan-tasks"><img src="https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/plan-tasks.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01067 |
| Opus 5 | $0.00009 | $0.00534 |
| Sonnet 5 | $0.00003 | $0.00213 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
plan-tasks 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 architect 角色创建实现计划，不编写应用代码。
本命令是任务拆解的便捷入口，不是任务卡的唯一生产方式。已有任务卡无论由谁创建，只要符合 CLAUDE.md 的文档生命周期和仓库门禁，都可以进入后续执行流程。
输入
读取 $ARGUMENTS、CLAUDE.md、docs/architecture.md、相关 App 文档、协议定义和现有代码。
需求包含 Figma URL 或 node-id 时，只复用 plan-figma 的“设计输入标准化”阶段读取节点，再返回本命令继续统一规划；不得让两个命令分别生成任务卡。
不得编造无法从产品输入、设计、协议或代码推导出的需求。未确定的产品决策必须显式记录。
规划规则
- 遵守
CLAUDE.md的任务卡生命周期、命名和必要元数据约定。 - 写入前扫描活动与归档任务，确保名称能区分当前任务且没有冲突；发生重名时使用更清晰的业务范围命名，无法区分时停止并报告。
- 文件 basename 同时作为依赖、Review、证据和 UI Spec 使用的任务标识。
本命令输出
创建：
docs/tasks/<task-slug>.md：可独立执行的任务卡。docs/figma/<context-slug>-design-context.md：仅在需要标准化 Figma 输入时生成，并由相关任务卡显式引用。
每张任务卡必须包含：
- 准确概括任务内容的一级标题。
executorfrontmatter，只允许task-executor、android-engineer、ios-engineer或bridge-engineer，并与platforms、workKinds的确定性路由一致。platformsfrontmatter 是无重复列表，元素限定为flutter、android、ios。只有纯documentation、planning或harness可以是[]，其他实现工作至少声明一个平台。workKindsfrontmatter 是非空无重复列表，元素限定为documentation、planning、harness、flutter、dart-client、capability-contract、native、bridge-adapter、bridge-contract、integration、quality-gate。blockedByfrontmatter，使用任务 slug 列表，无依赖时为[]；禁止重复、自依赖和循环依赖，全部任务必须构成可拓扑排序的 DAG。- 可选
securityReview: requiredfrontmatter。任务引入或改变认证/授权、敏感数据、网络或文件等外部输入、Deep Link/WebView、不可信输入反序列化、平台通道或原生权限、第三方依赖与执行脚本，或者 CI/MCP/Agent 的权限与执行能力时必须声明；普通 DTO 序列化、UI、文案、格式化、纯描述修正和不改变能力或行为的重构不声明。 - 输入和事实来源。
- 目标和非目标。
- 精确实现要求。
- 与实现同时编写的测试。
- 验收标准和验证命令。
- 平台或环境限制。
适用时按以下顺序安排基础契约与消费者：协议或持久化 Adapter、Domain Entity、Mapper、API、Controller、装配、Route、UI、集成验证。
涉及多个 Runtime 时，按所有权拆卡：Android Native Module、Android Bridge Adapter 和单平台
门禁使用 android-engineer；对应 iOS 工作使用 ios-engineer；Dart Client 与 Flutter Feature
使用 task-executor；Wire Contract 与多 Runtime 最终集成使用 bridge-engineer。不得让一个
平台 Agent 包办 Android、iOS 和 Dart，也不得把 Capability Contract 反向依赖 Wire Contract。
任务卡不得声明 uiSpec，也不得默认安排 Spec Auditor 或 App Operator。UI 自动化由人在普通任务流程之外单独调用 /plan-spec 与 /execute-ui-spec。
securityReview 是按风险触发的只读工程门禁，不是 UI 自动化，也不要求低风险任务或每个测试脚本接受人工审批。执行阶段仍会按实际 diff 兜底识别遗漏。
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.
- 5d ago First seen · 62 lines · 17 tokens per session scan A 1f9433b98c3b
plan-tasks is a command published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 24d ago), licensed MIT. It adds 17 tokens to every session and 1,067 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.