agentsop-repo-map

agentsop-repo-map is a skill for Claude Code, Codex from agentsope/SkillAlchemy. It costs 108 tokens per session (7,147 once invoked), scanned A, original, MIT.

A read-only map of a code repository that shows important classes and functions and how files refer to one another. It uses tree-sitter to extract symbols and PageRank-style ranking to fit the most relevant code into a token budget.

In plain words
What is it for?
Use it for renames, API changes, extracted functions, hooks, cross-file impact checks, and other tasks in larger source-code repositories.
Why use it?
It helps a coding agent find the right files in a large multi-file change instead of guessing paths or repeatedly editing the wrong code. Unlike vector search, the map is designed to be human-auditable and does not require an embedding index.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: built for aider.

Good fit Use it for renames, API changes, extracted functions, hooks, cross-file impact checks, and other tasks in larger source-code repositories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentsope/skillalchemy/agentsop-repo-map
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 agentsope/SkillAlchemy --skill agentsop-repo-map
Clone the repo
git clone --depth 1 https://github.com/agentsope/SkillAlchemy

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 agentsop-repo-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-repo-map.svg)](https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-repo-map)
Your own site
<a href="https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-repo-map"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-repo-map.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,147 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00108 $0.07147
Opus 5 $0.00054 $0.03573
Sonnet 5 $0.00022 $0.01429
Haiku 4.5 $0.00011 $0.00715

Measured 8d ago against content hash 5def8240359a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agentsop-repo-map 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 8d 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.

skills/agentsop-repo-map/SKILL.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo-Map — 让 LLM 在大仓库里找到正确文件

一句话:tree-sitter 抽取符号 → 在跨文件引用图上跑 PageRank → 按 token 预算把最重要的 class/function 签名作为只读地图塞进上下文。它不是 RAG、不维护向量索引、可被人审。Aider 用同样的机制在 SWE-Bench Lite 上把"正确文件命中率"打到 70.3% [aider.chat/2024/05/22/swe-bench-lite.html]。

这是一个工具技能(tool skill),不绑定 Aider;任何 coder-agent harness 只要能给 LLM 喂上下文,都可以接入或自建 repo-map。

1. 何时激活本技能

下列任一条件成立时,将"构建/刷新/使用 repo-map"作为该会话的标准动作:

  • 任务涉及 多文件编辑跨文件影响分析(rename、抽函数、改 API 签名、加 hook 点)。
  • 仓库 ≥ ~20 个源文件,或 LLM 无法靠记忆/猜测找到正确目标。
  • 你不想(或不能)维护 embedding 索引:环境无 GPU、不允许出仓数据、PR 评审需可追溯证据。
  • 你想给 LLM 可审计的导航地图(vs. 黑盒向量检索)。/map 一样的 dump 必须能给人看。
  • 多文件编辑后 LLM 反复改错文件、编造路径、SEARCH/REPLACE 找不到目标——典型的"没地图就乱走"信号。
  • 你在写自定义 coder agent,需要一个"廉价、确定性、即时刷新"的代码 context 原语。

不应激活的反面信号:单文件改动且文件已知;任务是从零起项目;二进制资产仓库;非源代码(CSV/data lake)—— 详见 §6。

2. 核心心智模型

2.1 三个原语 + 两个不变量

+----------------------+   +-----------------------+   +-----------------------+
| 1. tree-sitter       |   | 2. cross-file graph   |   | 3. token budget       |
|    symbol extraction |-->|    + PageRank-style   |-->|    (dynamic, shrink   |
|                      |   |    importance rank    |   |    when files added)  |
| - parse, no execute  |   | - nodes = files       |   | - default ~1k tokens  |
| - class / fn / sig   |   | - edges = symbol refs |   | - cap configurable    |
| - works offline,     |   | - PageRank picks      |   | - 0 = disabled        |
|   no LLM call        |   |   "most referenced"   |   |                       |
+----------------------+   +-----------------------+   +-----------------------+
                                       |
                                       v
                       +-----------------------------------+
                       | Output: skeleton text in prompt   |
                       | (NOT a tool-call, NOT a vector)   |
                       |                                   |
                       |   path/to/file.py:                |
                       |     class Auth:                   |
                       |       def login(user, pwd) -> T   |
                       |       def logout() -> None        |
                       |     def hash_password(pwd) -> str |
                       +-----------------------------------+

Read the full file on GitHub · 396 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. 8d ago First seen · 396 lines · 108 tokens per session scan A 5def8240359a

Subscribe to this mod's changes

agentsop-repo-map is a skill published in the GitHub repository agentsope/SkillAlchemy (370 stars, last pushed 6d ago), licensed MIT. It adds 108 tokens to every session and 7,147 once invoked, about $0.0005 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.