REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/axiomcodeai-axiomcodegraph)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 axiomcodegraph | rea | graphify | archify | security-audit-skill | |
|---|---|---|---|---|---|
| 作者 | AxiomCodeAI | morluto | Graphify-Labs | tt-a1i | cloudflare |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 693 | 461,751 | 148,352 | 96,757 | 73,156 |
| 最近代码更新 | 2026年11月10日 | 2026年11月16日 | 2026年11月16日 | 2026年11月15日 | 2026年9月15日 |
| 许可证 | – | MIT | Apache-2.0 | Apache-2.0 | MIT |
AxiomCodeAI 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodexCursorGemini CLIGitHub CopilotWindsurf
依据开发者 README 和 repo 中的文件夹
GitHub account AxiomCodeAI (organization) is only 2 months old: take extra care
★ 693 stars · code last changed 2026年11月10日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
Installing the maker’s way adds hooks that run without you asking: run on the BeforeAgent event · run on the BeforeTool event · run on the AfterTool event · run on the AfterAgent event · run every time a chat starts
Checked automatically from the repo files at commit 45ee8b1 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the skills/axiomcode folder again. The ZIP must have a axiomcode folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick axiomcode.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /axiomcode,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 axiomcode 文件夹放到 ~/.agents/skills/axiomcode
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 axiomcode
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: axiomcode
description: >-
Use for any why, what or where question about code — how a codebase works, where something lives, who calls it, what a change to it breaks, which tests cover an edit. Also use when resolving an issue or bug report, which names a symptom rather than a file. Examples: "How does X work?", "Where do I change Y?", "What calls this?", "What breaks if I change Z?", "Which tests do I run?", "Fix this issue". Search with grep as usual; ask the graph for what grep cannot know — which declaration a call reaches and the callers that never spell the name. Answers come from a resolved call graph, so they include callers that never spell the name — through an interface, an override, a callback, dependency injection or a config key — and every place comes with the code of the function it sits in. Call the MCP tools directly, no need to load this skill first: impact(name) for who calls it and what a change reaches (with no name: your uncommitted edits), path(start, end) for how A reaches B, tests() for the tests your edits reach, context(task, source=True) for how something works as a step-by-step call flow with each step's code. Only when those tools are not in your list, the same from the shell: `axiomcode impact <name>`, `axiomcode path <A> <B>`, `axiomcode tests`, `axiomcode context "<task>" --source`. Java, TypeScript, Python, JavaScript, C#, and HTML + CSS (impact .class, #id, a custom property as var(…), page.html, sheet.css, page.html:LINE; each language its own graph).
---
# axiomcode
Search with grep as usual; the graph answers what grep cannot. Use the MCP tools when they are in your list (in Claude Code
`mcp__plugin_axiomcode_axiomcode__impact`, `__path`, `__tests`, `__context`); otherwise run
`<this dir>/../../plugins/axiomcode/skills/axiomcode/scripts/axiomcode <verb>` from the repository root. Same answer either way.
| the question | MCP tool | shell |
|---|---|---|
| where is the code for this task? | your own search (grep), then bring the name here | — |
| who calls X, what does changing it reach, which tests? | `impact(name)` | `axiomcode impact <name>` |
| what is the value of constant X, and who reads it? | `impact(name)` | `axiomcode impact <name>` |
| what do my uncommitted edits reach? | `impact()` | `axiomcode impact` |
| how does A reach B? | `path(start, end)` | `axiomcode path <A> <B>` |
| which tests do my edits need, and how do I run them? | `tests()` | `axiomcode tests` |
| an answer lists an unresolved call I can see the target of | `link(site, target)` | `axiomcode link <file:line> <target>` |
| how does this work, start to finish? | `context(task, source=True)` | `axiomcode context "<task>" --source` |
Names are written as in the code: `Owner.method`, `function`, `Type`, or `file.py:123` for the declaration at that
line. There is no setup step: the first question builds the graph, and it refreshes itself after every edit.
## What an answer looks like
A numbered list of places, most relevant first, each with the code of the function it sits in. `→` marks the line
that matters; a short function is shown whole.
1. shop/pricing.py:6 [resolved · total]
```python
4 def total(prices):
5 net = sum(prices)
→ 6 return net * (1 + vat_rate())
```
verified: ✓ (4 edge(s) looked up again)
Answer from the code shown; open a file only for a place whose body was cut (`…`). The tag says how sure the place
is: `resolved` is an edge the engine resolved and re-checked (`verified:`), do not re-derive it by grepping;
`one of a set` is one of several real targets; `by name` and `text` are leads, not facts; `test` marks a test;
`hop N` is how far out it is. A call the graph could not resolve is *unknown*, not absent: never report "no callers"
from an empty answer.
## impact
With a name: who calls it, what depends on it further out, and the tests that exercise it. Example:
`impact(name="PriceService.total")`. With no name: the first line is `your edits:` (each declaration you changed and
how), then the same answer for all of them. A constant answers with its value — `change: const MAX_ITEMS = 5` —
so a limit, a default or a threshold is read off the first line rather than from the file.
## path
How one declaration reaches another: every hop of the call chain, with the code at the line each call is written on.
Example: `path(start="main", end="Ledger.put")`.
## tests
The tests your uncommitted edits reach, each with its code, and a last line `run: <command>` that runs exactly those.
Example: `tests()`. It is a lower bound: a test reached only through reflection or a service loader is not listed.
## link
Answers are in three parts. CONFIRMED places are backed by an edge: `resolved` by the engine, or `asserted` by a link —
act on them. LEADS are reached only through a guess (`by name`, `by key`, `one of a set`, `text`) — check each before
relying on it. TO RESOLVE lists the calls the answer stopped at: the site as `file:line:col`, the call as written, why
the engine could not follow it (a value from `getattr`, a handler table, reflection, a callback) and the graph's
candidate targets with their `file:line`.
When the task depends on one of those sites, read the call. Only if the code makes the target CERTAIN, record it:
`link(site="app/dispatch.py:6:12", target="on_save")`, or `axiomcode link app/dispatch.py:6:12 on_save` from the shell.
A candidate is a lead: confirm it by reading the call, never link one because it is ranked first. From then on impact,
path and tests walk that edge, labelled `[asserted]`, never `resolved`; when the target declares a return type, the
calls made on its result (chained, or on a variable assigned from it) resolve too. When a lead at a site is wrong,
reject it: `link(site, "not:<target>")` — it is no longer walked; only a guess can be rejected, never an edge the
engine resolved. The links are kept in `axiomcode-links.tsv` at the repository root, which is worth committing.
`link()` with no arguments lists them and whether the graph took each one; `axiomcode link <file:line:col> -` removes
one. A link is refused when the call written there names a different declaration, or the target is not one; when
the line it was made on is edited, it is dropped and listed as stale, and the site is to resolve again. Never link a
guess: an asserted edge is trusted by every answer after it.
## context
How something works, from a task in your own words: the files and callables the task touches and, for a
how-does-X-work question, the call flow step by step. Example: `context(task="how is an invoice settled",
source=True)` — source carries each step's code, so the flow is read without opening files. Only English task
words land (the graph's vocabulary is the code's identifiers); any language works once the task includes one
identifier as written in the code.
## index
`axiomcode index` builds the graph explicitly; `--lang` and `--src` narrow it. Never re-run it on an
existing graph: the graph rebuilds itself after edits, and an answer given before that finishes says so on a
`graph refresh:` line.
By default the graph is built without the project's dependencies: a call into one is unresolved or named only as an
external boundary. When better coverage is needed, compile the dependencies and enable them with `--library`, given
once on `index` and kept by every rebuild after it:
axiomcode index --library auto # the dependencies the project imports
axiomcode index --library .venv/lib/python3.12/site-packages/requests,/deps/ir/jdk # or name them
`auto` finds what the project depends on, in every language: a Python package its source imports, in its virtual
environment (`.venv`, `venv`, `$VIRTUAL_ENV`); a JavaScript / TypeScript package it imports, under `node_modules`; in a
Deno project, every `jsr:`, `npm:` and URL module it imports, from Deno's cache (`deno install` fetches them); a
Java dependen提问、分享技巧或报告无法使用。按“有帮助”数量排序。