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-specgit 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-spec)<a href="https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/plan-spec"><img src="https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/plan-spec.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 | $0.00022 | $0.00324 |
| Opus 5 | $0.00011 | $0.00162 |
| Sonnet 5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
plan-spec 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 4d 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.
What it actually says
只有用户明确要求规划 UI 自动化或显式调用本命令时，才使用 spec-writer 把 $ARGUMENTS 转换为 UI 行为 Spec。普通任务规划和执行不得自动进入本流程。
- 至少确认一个真实存在的任务卡、Figma 设计输入文档或原型文档。
- 读取
CLAUDE.md，加载ui-behavior-specSkill，并读取相关任务和设计输入。 - 区分产品事实、原型可见事实、工程可操作性和待决问题。
- 无论输入是否包含任务卡，Spec 都写入
docs/app-operator/specs/<spec-id>.spec.yaml；任务卡仅可作为sources之一，Spec 不随任务归档移动。 - 运行
make spec-check。 - 汇报
draft/ready状态、来源和待决问题。ready只表示行为契约可以在实现存在后由人显式交给/execute-ui-spec，不改变任何任务状态；draft停止并请求补充待决产品信息。
不得调用 spec-auditor 或 app-operator，不得为了让 Spec 可执行而编造数据、错误态或成功条件。
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.
- 4d ago First seen · 16 lines · 22 tokens per session scan A 0a907787c949
plan-spec is a command published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 24d ago), licensed MIT. It adds 22 tokens to every session and 324 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
generate_application_test_plan
Khám phá ứng dụng web, sinh test plan và test scenarios. Hỗ trợ 2 mode — PLAN (chỉ test plan) và FULL (test plan + automation skeleton).
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
verify-pr
Verify a PR's frontend changes through browser automation.
harness-eval
执行 Harness 四级任务验证，覆盖编译、契约、E2E 与 Constitution 审查。.
test-run
Run E2E tests with qa-use CLI.
record
Record the browser while validating a flow, then judge it against a rubric.