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 skills add smallnest/goal-workflow --skill understandgit clone --depth 1 https://github.com/smallnest/goal-workflowWrote 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/skills/smallnest/goal-workflow/understand)<a href="https://agentmods.dev/skills/smallnest/goal-workflow/understand"><img src="https://agentmods.dev/badge/skills/smallnest/goal-workflow/understand/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.
<a href="https://agentmods.dev/skills/smallnest/goal-workflow/understand"><img src="https://agentmods.dev/badge/skills/smallnest/goal-workflow/understand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00125 | $0.02172 |
| Opus 5.5 | $0.00050 | $0.00869 |
| Sonnet 5.5 | $0.00025 | $0.00434 |
| Haiku 4.5 | $0.00013 | $0.00217 |
Grade A, and why
understand scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
understand
把「本次(AI)新生成的代码变更」变成一个可交互的审阅网页:左侧按真实项目布局列出变更文件树,右侧显示所选文件的 diff(高亮、增删与未变更代码明显区分),并在右侧边栏逐段给出相关单位需求与代码解释;解释下方可按需提供「伪代码」「调用树」两个展开式文本视图(参考 show-me skill 的呈现方式)。
始终用中文产出解释与需求。
何时用
- 用户说
/understand、"review 这次改动"、"解释下新写的代码"、"看看这次变更做了啥"。 - 目标是理解 + 审阅当前工作区里尚未吃透的改动(通常是 AI 刚生成的),不是重构或修 bug。
组成
skill 目录下三件套(都在 ~/.claude/skills/understand/):
understand.py— 纯标准库生成器,两个子命令:scan(解析 git diff →data.json+annotations.json骨架)、render(合并注释 →report.html)。template.html— Claude light 主题两栏页面(占位符__UNDERSTAND_PAYLOAD__注入数据),Prism.js 走 CDN 做语法高亮。- 本文件 — 流程说明。
执行流程
在**用户当前工作目录(仓库内)**执行以下步骤。全程把 SKILL_DIR 当作本 skill 目录的绝对路径(即本文件所在目录)。
1. 扫描变更
python3 "$SKILL_DIR/understand.py" scan
- 默认基线 = 当前分支与主分支(origin/main→main→master)的 merge-base;如用户指定范围可加
--base <ref>(例如只看最后一次提交用--base HEAD~1)。 - 默认输出目录
.understand/(相对 CWD)。可用--out <dir>改。 - 它覆盖:已提交(base..HEAD) + 已暂存 + 未暂存 + 未跟踪新文件。
- 命令会打印 JSON:文件数、增删行数、
data.json/annotations.json路径、以及paths(变更文件列表)。读这个输出了解改了哪些文件。
2. 通读改动并撰写注释
先把改动读懂,再落注释。建议:
Read每个变更文件(结合data.json里的 hunks 看具体增删行号),必要时读周边未改代码补足上下文。- 判断每处改动对应的单位需求:优先从仓库线索找真实依据——commit message、
docs/需求文档、代码注释里写的需求编号/背景、相关 issue。找到真实需求就照写;确实找不到,就基于代码逻辑写「推测意图」并在注释里把inferred置为true(前端会标成灰色「推测意图」而非「需求」,避免把猜测伪装成事实)。
然后编辑 .understand/annotations.json(scan 已生成骨架,保留其 files[].path 顺序,逐个填充)。结构:
{
"title": "本次变更的一句话主题",
"summary": "整体在做什么、为什么(2~4 句,可用 **加粗** 与 `代码`)",
"files": [
{
"path": "src/main/java/.../PwaTierInvitationService.java",
"summary": "这个文件这次改了什么、为何改(1~3 句)",
"annotations": [
{
"side": "new",
"start": 52,
"end": 53,
"requirement": "expires_at 为 timestamptz,需正确编码",
"explanation": "Vert.x PG 客户端不支持 `java.time.Instant`,改绑 `OffsetDateTime`(`atOffset(UTC)`),否则运行期报 coercion 错误。",
"pseudocode": "on(save)\n if content is unchanged\n return cached result\n write new content\n return fresh result",
"callTree": "submitForm\n createSession\n persistPrompt\n launchAgent\n navigateToSession",
"inferred": false
}
]
}
]
}
What ships with it
2 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.
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.
- 1mo ago Changed · +6 lines 337a1bfb4198
- 1mo ago First seen · 102 lines · 125 tokens per session scan A 878dde837fcb
understand is a skill published in the GitHub repository smallnest/goal-workflow (293 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 2,172 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
review-resolution
You MUST use this when code-review findings, PR comments, CI review output, or reviewer suggestions need technical validation before any fix or disposition, including feedback from human reviewers, subagents, GitHub, static-analysis tools, or external review systems.
verification-gate
You MUST use this when work is about to be called complete, done, fixed, ready, or mergeable - before a completion claim, a merge or pull request, a branch finish, or a handoff report.
cross-review
You MUST use this when an implementation plan or a finished implementation needs an independent review by other agent CLIs - by default the opposite CLI (Codex for work done in Claude Code, Claude Code for work done in Codex) together with Antigravity (Gemini) - whether the user asks for a cross-review or a second…
review-request
You MUST use this when a completed or partially committed implementation needs an independent code review against explicit requirements, a defined task scope, and the actual Git diff, including committed and working-tree changes.
criticism-self-criticism
A structured review method for examining completed work, criticism, and repeated mistakes. It focuses on specific evidence, causes, effects, and practical improvements.
validate-issue
Use when the user asks to validate, review, or check a GitHub issue against the code. Returns a cited update decision with a complexity score, or a cited close recommendation when the issue is already completed or invalid.