software-health

software-health is a skill for Claude Code, Codex from tianemon/EasyMint. It costs 67 tokens per session (1,760 once invoked), scanned A, original, MIT.

A software-health review process that checks whether an application behaves as promised and handles failures, resources, performance, and connected components correctly.

In plain words
What is it for?
Use it for scoped change reviews, module checks, application-wide behavior reviews, regression investigation, and recovery or performance problems.
Why use it?
It helps locate issues such as stuck operations, incorrect state, unreleased resources, slow behavior, and failures that cannot recover or be diagnosed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for scoped change reviews, module checks, application-wide behavior reviews, regression investigation, and recovery or performance problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tianemon/easymint/software-health
Install

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.

Any agent
npx skills add tianemon/EasyMint --skill software-health
Clone the repo
git clone --depth 1 https://github.com/tianemon/EasyMint

Made for: Claude Code, Codex.

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 software-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/tianemon/easymint/software-health/github.svg)](https://agentmods.dev/skills/tianemon/easymint/software-health)
Your own site
<a href="https://agentmods.dev/skills/tianemon/easymint/software-health"><img src="https://agentmods.dev/badge/skills/tianemon/easymint/software-health/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 software-health

Your own site · 80×15
<a href="https://agentmods.dev/skills/tianemon/easymint/software-health"><img src="https://agentmods.dev/badge/skills/tianemon/easymint/software-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,760 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 $0.00067 $0.01760
Opus 5.5 $0.00027 $0.00704
Sonnet 5.5 $0.00013 $0.00352
Haiku 4.5 $0.00007 $0.00176

Measured 5d ago against content hash 74e2cfd6dbec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

software-health 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.

resources/skills/software-health/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

软件健康维护

目标是让软件的实际行为、调用方或用户观察到的结果与声明的能力保持一致,并让失败能够收尾、恢复和定位。以可复现的行为及证据判断健康性,不以测试数量、代码行数、报告篇幅或统一评分替代判断。

适用于不同项目与技术栈。检查项按实际入口、运行方式、数据和依赖风险选择;界面、后台任务、模型调用、发布或迁移等环节仅在项目存在且本次范围相关时检查,不预设特定产品、SDK、框架、构建命令或仓库布局。

确定本次工作边界

先读取项目规则、现有变更、运行入口与验证命令,识别项目类型和已有约定。优先复用现有检查,避免引入重复工具链。

区分用户要的是审查建议、执行检查,还是检查并修复。已授权的工作直接推进;只要求审查时不修改产品。启动应用、真实网络/模型请求、生产故障注入、发布等动作按现有授权判断,不因技能被调用就扩大权限,也不对已授权动作重复确认。

选择当前风险相关的检查项,而非固定执行全部项目。局部维护沿改动及其上下游检查;整体审查覆盖高频用户流程和高后果失败路径;发版检查围绕候选版本及明确支持的升级来源。发现具体风险再加深,不把猜测扩展成无边界重构。

按本次问题选择参考,不默认全部加载:

本次范围 参考与重点
指定提交、差异或修复复核 references/change-review.md:需求对账、影响清单、断言有效性、变更归属
模块、页面或子系统的现有实现 references/module-audit.md:入口、契约、字段消费与行为闭环
整体运行、卡顿、故障恢复或升级风险 references/checks.md:状态、并发、资源、性能与兼容性
问题涉及 AI 指令、模型行为或工具调用 references/ai-contracts.md:最终上下文与运行能力

多个范围并存时,以用户目标为主线补充相关参考,不因此扩大成全仓扫描。已有审查结果时复用其结论及证据,只补尚未覆盖的健康风险,不依赖其他技能存在,也避免重复审查。

用用户流程建立检查对象

从关键入口追踪完整路径:用户动作或调用请求 → 请求/事件 → 状态变化 → 副作用与持久化 → 用户反馈或返回结果 → 收尾或恢复。覆盖相关的客户端、服务、后台任务和外部依赖,不把单个函数成功等同于整条流程完成。

为实际风险写出可验证的不变量。例如:

  • 显示的运行状态对应真实工作;取消之后不会静默重新开始。
  • 每个操作绑定正确的用户、项目、会话或资源;消息载荷不能覆盖可信通道身份。
  • 配置变化作用于约定的时机,执行端与展示端对“何时生效”理解一致。
  • 失败、取消和超时都能终结等待;重试不会重复产生不可接受的副作用。
  • 资源在其所有者结束后释放;仍被后台任务使用的资源不会提前销毁。

这些是不变量示例,按项目取舍;不用为无关状态新建通用框架。

从怀疑推进到证据

结合静态引用、类型/规范检查、状态与事件追踪、测试和运行实测。区分“已复现”“由源码可确定”“尚待验证”,不要把低引用次数、一次超时或单次内存上升直接判为缺陷。

发现问题时记录触发条件、预期、实际结果、位置和影响。将需求、说明及文案中的承诺对应到真实代码路径;核对按名字列举的清单和字段的最终消费方。适合自动化的行为先写失败用例,再修复;难以自动化的保留最小复现和核验方法。验证完整调用链的可观察结果,避免只用测试重复实现中的判断。

复核修复时检查断言能否区分已知错误与正确实现,失败是否确实来自目标行为。破坏性探针放在隔离副本中;不能为验证测试而还原用户工作树、搬动他人的改动或改写提交。

运行时验证优先使用隔离数据和可控依赖,覆盖代表性的成功、失败与中断路径。检查临时目录以外的端口、账户、全局配置和后台任务是否也得到隔离。测试结束停止自建进程、释放连接并仅清理自建资源;用户既有数据按其明确授权范围处理。

真实模型或外部服务评测在授权范围内控制调用次数、耗时和成本,明确停止条件。没有授权或条件不足时继续可做的本地验证,并记录限制,不把模拟结果冒充真实服务结果。

修复与清理的判断

在授权范围内修复已证实且局部可恢复的问题。涉及产品语义、视觉取舍、公共兼容边界、费用或大规模结构调整时,先完成可独立验证的部分,再说明具体取舍。

死代码清理先核对动态入口、配置注册、生成物、测试观察点和外部消费者。确认无用途后清理整条残留链,更新相关声明和失效测试。兼容迁移按支持版本与旧数据验证退役;停止读取旧文件,不等于可以删除用户历史数据或解除遗留凭据保护。

Read the full file on GitHub · 80 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 80 lines · 67 tokens per session scan A 74e2cfd6dbec

Subscribe to this mod's changes

software-health is a skill published in the GitHub repository tianemon/EasyMint (79 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 1,760 once invoked, about $0.0003 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 2026-10-11.

Related

Other skills, from other repositories

qa

Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.

FlorianBruniaux/claude-code-ultimate-guide · 23 tokens

eval-hooks

Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented…

FlorianBruniaux/claude-code-ultimate-guide · 115 tokens

check-cache-bugs

Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.

FlorianBruniaux/claude-code-ultimate-guide · 38 tokens

sandbox-unblock

Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…

FlorianBruniaux/claude-code-ultimate-guide · 65 tokens

investigate

Systematic root-cause debugging: find the cause before writing any fix.

FlorianBruniaux/claude-code-ultimate-guide · 17 tokens

plan-pipeline-execute

Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.

FlorianBruniaux/claude-code-ultimate-guide · 43 tokens