Nexus: Skill for Claude Code

.claude/skills/devflow/agents/release/SKILL.md

test-release is a skill for Claude Code from MT-gar/Nexus. It costs 36 tokens per session (941 once invoked), scanned A, original, MIT.

A controlled release workflow that creates a release, waits for approval, runs automated tests, checks a limited rollout, and confirms or rolls back the change. A rollback returns the service to a recorded earlier version when validation fails.

In plain words
What is it for?
It is for publishing repaired code, running build, unit, and integration checks, validating a gradual rollout, and recording failed releases or rollbacks.
Why use it?
It reduces the risk of deploying a faulty change by requiring approval and checking the change before full release.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is MT-gar/Nexus's own configuration. It tells Claude Code how to work on Nexus 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 Nexus configures →

View source ↗ MT-gar/Nexus
Reuse

Borrowing it

Nothing to install: this file belongs to MT-gar/Nexus. 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/MT-gar/Nexus/main/.claude/skills/devflow/agents/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MT-gar/Nexus

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 test-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/mt-gar/nexus/release/github.svg)](https://agentmods.dev/skills/mt-gar/nexus/release)
Your own site
<a href="https://agentmods.dev/skills/mt-gar/nexus/release"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/release/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for test-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/mt-gar/nexus/release"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 941 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 $0.00036 $0.00941
Opus 5.5 $0.00014 $0.00376
Sonnet 5.5 $0.00007 $0.00188
Haiku 4.5 $0.00004 $0.00094

Measured 1mo ago against content hash b802d2374163, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-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 1mo 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/skills/devflow/agents/release/SKILL.md · 72 lines

What it actually says

Skill:test-release(自动化测试发布)

1. 业务用途

将修复后的代码通过受控流程发布上线:创建发布(自动发起人工审批,强制回滚计划)→ 自动化测试 → 灰度验证 → 确认上线;验证失败自动回滚(记录回滚目标版本与原因)。对应 8 步闭环的"结果验证"与"审批与回滚"环节。

2. 输入输出 Schema

输入:

{ 发布任务: { task_id, description: 变更摘要 + 缺陷 ID 列表 },
  版本建议: { version: string, previous_version: string } }

输出:

{ 发布: { release_id, version, status, approval_id },
  测试结果: { 构建: ok|failed, 单测: { 通过, 失败 }, 集成测试: ok|failed },
  验证结论: { 结果: live|failed|rolled_back, 证据: string, rollback: { target_version, reason }? } }

3. 调用触发条件

  • manager 创建"发布任务"(依赖修复任务完成)
  • 灰度/线上监控发现异常需要回滚(可直接 rollback_release)

4. 依赖工具

工具 用途
create_release 创建发布(默认自动发起 high 风险审批,状态 pending_approval)
update_release 状态流转:testing → verifying → live/failed(服务端强制审批门禁)
rollback_release 失败回滚:记录 target_version/reason,置 rolled_back(幂等保护)
list_approvals 轮询审批结果
list_releases 发布历史核对(版本唯一性)
客户端原生能力 构建、单元/集成测试执行、灰度流量操作

5. 失败重试 / 降级机制

  • 测试失败 / 灰度验证失败 → update_release(status="failed") → rollback_release(reason=...)(自动回滚,全链路审计)
  • 审批被拒 → 报告 manager,不强行发布;调整方案后重新 create_release
  • 审批超时 → 提醒用户,保持 pending_approval,不自动放行
  • 降级:无灰度环境 → 以自动化测试为准 live,并在交付消息中标注"未做灰度验证"

6. 安全权限边界

  • ✅ 允许:create_release / update_release / rollback_release / list_approvals
  • ❌ 禁止:approve_request / reject_request(发布审批只能人工执行,服务端有门禁双重保证)
  • ⚠️ 版本唯一性由服务端强制(重复版本拒绝创建)
  • ⚠️ 回滚是安全操作必须有 reason;回滚动作本身写入审计日志(谁/何时/为什么/回滚到哪)

7. 多场景复用价值

  • 软件发布管理(本场景)
  • 灰度发布与回滚(任何服务上线流程)
  • 配置变更发布(配置灰度 + 自动回滚 — 配置治理方向)
  • 依赖升级验证(自动化测试前置的依赖变更发布)

8. 与多 Agent 协作链路

fixer-agent ──修复交付──▶ devflow-manager ──发布任务──▶ release-agent
release-agent ──审批请求──▶ devflow-manager ──展示──▶ 用户(人工审批)
release-agent ──live/failed──▶ devflow-manager ──复盘任务──▶ retro-agent

发布状态机 + 审批门禁 + 回滚语义是"结果验证"与"审批与回滚"两个闭环环节的工程支撑。

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. 1mo ago First seen · 72 lines · 36 tokens per session scan A b802d2374163

Subscribe to this mod's changes

test-release is a skill published in the GitHub repository MT-gar/Nexus (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 941 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-20.

Related

Other skills, from other repositories

cloudflare-workers-testing

Comprehensive testing guide for Cloudflare Workers using Vitest and @cloudflare/vitest-pool-workers. Use for test setup, binding mocks (D1/KV/R2/DO), integration tests, or encountering test failures, mock errors, coverage issues.

secondsky/claude-skills · 57 tokens

test-migration

Migrate a test suite from one framework to another, incrementally and without losing coverage. Covers Selenium→Playwright, Cypress→Playwright, Jest→Vitest, Mocha→Vitest, and Protractor→Playwright, with parallel CI running, locator/assertion translation, and a coverage-parity track. Use when: "migrate tests," "switch…

petrkindlmann/qa-skills · 178 tokens

unit-testing

Write effective unit tests with Jest, Vitest, or pytest. Covers the test-doubles taxonomy (stub/spy/mock/fake), Arrange-Act-Assert, coverage threshold configuration and CI gating, snapshot testing, fake timers, and mutation testing with Stryker/mutmut. Use when: "unit test," "Jest," "Vitest," "pytest," "mock,"…

petrkindlmann/qa-skills · 174 tokens

Code Coverage Analysis

Measure and enforce test coverage with Istanbul/nyc, c8, Jest, and Vitest. Covers branch versus line coverage, per-directory thresholds, CI gates, and correctly excluding generated code from reports.

PramodDutta/qaskills · 45 tokens

matlab-testing-ci

MATLAB testing, validation, and CI workflow for matlab.unittest, MATLAB Test, Simulink Test, coverage, artifact generation, GitHub Actions, and open-source reproducibility. Use whenever MATLAB work needs verification, regression tests, CI, GitHub publication, or acceptance criteria.

wzyn20051216/matlab-agent-skills · 62 tokens

qa-ci-cd-testing

Guidance for adding automated tests to a CI/CD pipeline, the process that checks and delivers software changes.

Kokxi/qa-test-skills · 204 tokens