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/review-changesgit 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/review-changes)<a href="https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/review-changes"><img src="https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/review-changes.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 | $0.00014 | $0.00703 |
| Opus 5 | $0.00007 | $0.00351 |
| Sonnet 5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
review-changes 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.
What it actually says
对当前改动执行只读 Review。调用工作流可以在启动普通 Review Profile 前运行非破坏性验证，并把命令、 退出码和未经结论加工的原始证据交给对应 Reviewer；Reviewer 自身只读取文件、diff 和已有证据， 不运行命令。调用工作流可以写 Review 报告，但不得修改实现、测试、配置或依赖。
首轮审查
任务模式读取活动任务完整 workKinds，按 /execute-tasks 的固定映射选择一个或多个
code-reviewer、harness-reviewer、contract-reviewer。独立 scope 没有任务卡时，调用方必须提供
明确 workKinds，或提供足以唯一确定普通 Profile 且不存在歧义的范围；否则停止，不根据文件扩展名猜测。
根据用户请求、任务卡或分支确定目标 diff，并保护无关工作树改动。多个 Profile 绑定同一冻结候选，彼此
不得读取结论；支持时并行运行，不支持时顺序运行。
写报告前先解析 scope。任务 Review 只接受 canonical 活动任务，并写入固定的
docs/reviews/execute-<task-slug>.md；报告使用 reviewFormat: routed-v1，声明与映射相同的有序
reviewProfiles，正文按 Profile 分节且每条发现带 ownerProfile，聚合 p0、p1 是所有 Profile 当前
未解决数量之和。任务已经位于 docs/tasks/done/ 时停止，不得覆盖或追加归档报告。
独立 scope 必须是 canonical lowercase kebab-case，且不得等于活动或归档任务的 execute-<slug>、
security-<slug> 报告名，也不得覆盖既有任务报告。检查通过后写入 docs/reviews/<scope>.md，按严重级别排序：
- P0：安全、数据丢失、崩溃、构建失败、严重正确性问题或不兼容公共/wire 契约，阻断完成。
- P1：高概率回归、架构越界、生命周期泄漏、缺少必需行为或关键测试缺口，阻断完成。
- P2：维护性或低风险质量建议，可以显式延后。
每条问题必须包含文件行号、影响、证据和明确修法。
若报告对应的旧问题已经被其他改动修复，先根据报告的 task slug 检查所属任务状态。任务仍处于活动状态时，可以在同一报告追加“复审”章节；任务已经位于 docs/tasks/done/ 时，原报告是不可变历史快照，必须使用新的活动任务与新 scope 写入独立报告，不得追加或更新原报告。两种情况都不得自行实施修复。
交付报告路径、各级问题、验证结果和剩余风险。需要修复时，等待用户明确调用 /fix-review-findings <review-report-path>。
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 · 34 lines · 14 tokens per session scan A 32385f2e086e
review-changes is a command published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 703 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.