flutter-ai-harness: Command for Claude Code

.claude/commands/review-security.md

review-security is a command for Claude Code from bladeofgod/flutter-ai-harness. It costs 33 tokens per session (877 once invoked), scanned A, original, MIT.

A read-only security review command for a specified task, code change, design, or threat model.

In plain words
What is it for?
Use it to review repository changes or supplied code, run relevant safe checks, and produce a security report with findings and evidence.
Why use it?
It looks for risks involving trust boundaries, sensitive information, outside input, dependencies, and changes to what an agent can do without modifying the implementation.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is bladeofgod/flutter-ai-harness's own configuration. It tells Claude Code how to work on flutter-ai-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flutter-ai-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bladeofgod/flutter-ai-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bladeofgod/flutter-ai-harness/main/.claude/commands/review-security.md
Clone the repo
git clone --depth 1 https://github.com/bladeofgod/flutter-ai-harness

Made for: Claude Code.

Wrote 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.

agentmods badge for review-security

README.md
[![agentmods](https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/review-security.svg)](https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/review-security)
Your own site
<a href="https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/review-security"><img src="https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/review-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00877
Opus 5 $0.00016 $0.00439
Sonnet 5 $0.00007 $0.00175
Haiku 4.5 $0.00003 $0.00088

Measured 7d ago against content hash 81910dda4729, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-security 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 7d 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.

.claude/commands/review-security.md · 42 lines

What it actually says

$ARGUMENTS 指定的任务、diff 或直接提供的代码执行只读安全审查。调用工作流可以运行非破坏性验证和写报告;security-reviewer 本身只读文件与原始证据,不执行命令,也不得修改实现、测试、配置或依赖。

输入模式

任务门禁

  1. 任务门禁只接受仓库 docs/tasks/ 直属目录下 canonical lowercase kebab-case 的活动任务普通文件; docs/tasks/done/、符号链接、特殊节点、子目录和仓库外路径必须在读取或写报告前拒绝。读取完整任务、 相关项目契约和测试证据,并将任务 slug 作为报告标识。
  2. 使用调用方给出的 Git Range、工作树或文件列表;缺少可确定的范围时停止,不猜测历史 baseline。
  3. 调用方识别本次实际审查的一个或多个仓库实现文件,并在审查完成后运行 bash scripts/dart-tool.sh run tool/implementation_digest.dart <repository-relative-path>...
  4. 只为该活动任务写入固定的 docs/reviews/security-<task-slug>.md;写入前检查目标没有属于已归档任务, 不得覆盖或追加任何归档报告。报告 frontmatter 包含 task、status、p0、p1、implementationFiles 和 implementationDigest。摘要必须在所属任务归档前与该任务的最终文件内容一致,否则不得归档;归档后 该报告作为历史快照保留。

独立审查

用户直接提供代码片段、设计、威胁模型或其他没有仓库文件的输入时也可以审查。此模式不强制绑定文件,默认在对话中返回结果;只有用户明确要求留档时才使用 canonical lowercase kebab-case scope 写入新文件 docs/reviews/security-<scope>.md。写入前必须确认 scope 不等于任何活动或归档任务 slug、目标不是既有任务报告且不会覆盖现有报告;冲突时停止并要求新 scope。这类报告必须声明输入范围,只覆盖当次输入,不使用任务 frontmatter,也不能作为任务归档门禁。

执行

  1. 首轮使用 security-reviewer 独立审查,不向其提供任何普通 Review Profile 的结论;它与普通 Profile 绑定同一冻结候选,运行环境支持时可并行启动,不支持时顺序运行但仍保持输入独立。
  2. 调用工作流只运行与安全假设直接相关的非破坏性验证,并把原始结果交给 Reviewer;不得让 Reviewer 自行执行 Bash。
  3. 静态分析、测试或构建已经失败时准确记录,不用安全审查掩盖基础门禁失败。

报告

  • 每条发现必须包含严重级别、资产、攻击者可控入口、危险操作或敏感数据路径、文件行号证据、影响和明确修法。
  • 任务报告的 P0/P1 未清零时不得标记 passed;任务归档前,Security Review 后任一 implementationFiles 内容变化时必须重新审查并更新摘要。
  • 已归档 Security Review 是任务完成时的不可变历史快照,不持续认证后来文件内容。后续任务修改同一 文件或修复历史问题时创建新的活动任务、diff、Review、Evidence 和摘要,不回写归档报告。

需要修复时等待用户明确调用 /fix-review-findings <security-review-path>;由 /execute-tasks 调用时,沿用其已有实现授权和最多三轮修复限制。

Changes

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.

  1. 7d ago First seen · 42 lines · 33 tokens per session scan A 81910dda4729

Subscribe to this mod's changes

review-security is a command published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 877 once invoked, about $0.0002 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.