flutter-ai-harness: Command for Claude Code

.claude/commands/check-release.md

check-release is a command for Claude Code from bladeofgod/flutter-ai-harness. It costs 12 tokens per session (758 once invoked), scanned A, original, MIT.

A release-readiness command that checks whether a code repository meets its rules for a new version, without publishing anything.

In plain words
What is it for?
Use it to inspect a planned release, run required checks, validate release files and version names, and write a release review report.
Why use it?
It helps catch missing reviews, tests, security checks, generated files, dependencies, configuration, and rollback details before release. It also prevents accidental tagging, uploading, publishing, or pushing.

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/check-release.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 check-release

README.md
[![agentmods](https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/check-release.svg)](https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/check-release)
Your own site
<a href="https://agentmods.dev/commands/bladeofgod/flutter-ai-harness/check-release"><img src="https://agentmods.dev/badge/commands/bladeofgod/flutter-ai-harness/check-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.00758
Opus 5 $0.00006 $0.00379
Sonnet 5 $0.00002 $0.00152
Haiku 4.5 $0.00001 $0.00076

Measured 7d ago against content hash 910cb22723cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

check-release 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/check-release.md · 42 lines

What it actually says

执行发版就绪检查。用户未明确要求时,不打 Tag、不上传、不发布、不 push。

检查项

  1. 确认发布范围和基线 Commit。
  2. 确认计划任务已完成或显式延后。
  3. 确认发布范围内的新任务普通 Review 格式为 routed-v1,其 reviewProfiles 与任务 workKinds 固定映射 一致,各 Profile 已有完成的独立结论且聚合 P0/P1 清零;既有 legacy 归档报告继续按历史格式兼容。
  4. 对声明 securityReview: required 的任务确认 security-<task-slug>.md 已通过,并由 make harness-check 验证归档快照 metadata、依赖与产物结构。发版检查不要求全部历史 implementationDigest 匹配发布时的 当前文件,也不把历史快照解释为对后来内容的批准;本次发布范围的安全变化必须由对应的新活动任务、 Security Review、Evidence 和摘要覆盖。独立代码片段审查不能替代任务报告,未涉及安全边界的 发布不额外触发。
  5. 运行 make check 和必要的代码生成同步检查。已有 UI Spec 只做 Schema 一致性检查,不要求 Audit 或 Run 齐全。
  6. 只有用户把某个 UI Spec 明确列入本次发布门禁时,才检查其 Audit、实现摘要和用户指定平台的 App Operator 报告;不得从任务卡或 Spec 的存在自动推导该门禁。
  7. 存在完整用户旅程或 Plugin/Bridge 改动时,使用 make integration-test INTEGRATION_DEVICE=<device-id> 运行集成测试,并构建受影响平台;CI 的 Android/iOS Debug Job 必须通过。
  8. 检查 Bridge 契约版本和变更日志。
  9. 检查生成产物、依赖锁、发布配置、签名占位和敏感信息扫描。
  10. 检查用户可见变化、已知限制和回滚考虑。

产物

写报告前把版本解析为匹配 ^[a-z0-9]+(?:[.-][a-z0-9]+)*$ 的 lowercase 单段 token;拒绝斜杠、 反斜杠、空段、...、URI 编码、控制字符和其他可改变路径语义的输入。词法规范化 docs/reviews/release-<version>.md 后,必须确认目标仍是 docs/reviews/ 的直属路径,仓库根和 docs/reviews/ 都是非符号链接普通目录,且目标不存在。目标已经是文件、目录、符号链接或其他节点时 停止并要求新的版本标识;不得覆盖或追加任何已有任务报告、独立 Review 或历史发版报告。

检查通过后写入 docs/reviews/release-<version>.md,包含:

  • 每个门禁的通过/失败结论。
  • 精确命令证据。
  • P0/P1 阻塞项。
  • 延后风险和负责人。
  • 本地未验证平台。
  • 最终建议:可发布、有条件可发布或不可发布。
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 · 12 tokens per session scan A 910cb22723cf

Subscribe to this mod's changes

check-release is a command published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 758 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.