← 返回 Skills 市场

Nm Conserve Context Map

Name: Nm Conserve Context Map
Author: athola

作者 athola · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install nm-conserve-context-map

功能描述

Generates a compressed project context map to avoid expensive Read/Grep calls. Use at session start or before implementing features in an unfamiliar codebase

使用说明 (SKILL.md)

Night Market Skill — ported from claude-night-market/conserve. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Context Map

Generate a compressed context map for the current project. The map pre-compiles structural knowledge that AI assistants would otherwise discover through expensive Read/Grep calls, saving thousands of tokens per session.

When to Use

At the start of a session to understand project layout
Before implementing features to identify entry points
When exploring an unfamiliar codebase
To reduce token waste from Read calls
To identify hot files (high blast radius) before changes

What It Detects

Category	Description
Structure	Directory layout with file counts and languages
Dependencies	Multi-ecosystem: Python, Node, Rust, Go, Java
Frameworks	Framework detection from dependency analysis
Entry Points	main.py, index.ts, CLI scripts, etc.
Import Graph	File-to-file import relationships
Hot Files	Files imported by 3+ others (high blast radius)
Routes	FastAPI, Flask, Express, Hono API endpoints
Env Vars	Environment variable references with defaults
Middleware	Auth, CORS, rate-limit, logging patterns
Models/Schemas	SQLAlchemy, Django, Pydantic, Prisma definitions
Token Savings	Estimated tokens saved vs manual exploration

Procedure

Run the scanner on the project root:

PYTHONPATH="$(find . -path '*/conserve/scripts' -type d \
  -print -quit 2>/dev/null || \
  echo 'plugins/conserve/scripts')" \
  python3 -m context_scanner .

Present the output to the user as the project overview.
Use the context map to guide subsequent file reads. Prioritize hot files and entry points first.

Options

Output

--format json for structured output
--max-tokens N to adjust output size (default: 5000)
--output FILE to save to a file

Modes

--blast FILE to show blast radius for a specific file
--section NAME to output a single section (routes, deps, env, hot-files, models, structure, middleware, frameworks)
--wiki-only to generate wiki articles without stdout

Opt-out

--no-cache to force a fresh scan
--no-wiki to skip wiki article generation

Wiki Articles

The scanner generates per-topic knowledge articles in .codesight/ for selective context loading:

python3 scanner.py .
# Creates .codesight/INDEX.md, auth.md, database.md, etc.

Load only what you need per session instead of the full map:

python3 scanner.py --section routes .
# ~200 tokens vs ~5,000 for the full map

Example Output

# Context Map: myproject
Files: 127

## Structure
  src                  42 files (Python)
  tests                18 files (Python)
  docs                  5 files (Markdown)

## Dependencies (Python)
Package manager: uv
  - fastapi 0.104.0
  - pydantic 2.5.0
  - sqlalchemy 2.0.0
  ...12 more

## Frameworks Detected
  - FastAPI
  - SQLAlchemy
  - Pytest

## Routes
  GET    /users          (src/routes/users.py)
  POST   /users          (src/routes/users.py)
  GET    /users/{id}     (src/routes/users.py)

## Hot Files (high blast radius)
  - src/models/base.py (12 importers)
  - src/utils/auth.py (8 importers)

## Environment Variables
  - DATABASE_URL (required)
  - SECRET_KEY (has default)

## Token Savings: ~12,600 tokens saved
  Routes: ~1,200
  Hot files: ~300
  Env vars: ~200
  File scanning: ~10,200

安全使用建议

Install only if you want an agent to scan and summarize your local project. Use it on intended repositories, consider --no-wiki if you want to avoid creating .codesight/ files, and be aware that broad trigger words may cause the skill to be selected more often than expected.

能力评估

✓ Purpose & Capability

The stated purpose is to summarize a codebase by structure, dependencies, imports, routes, environment variable references, and related project metadata; those capabilities match the advertised context-map function.

ℹ Instruction Scope

The runtime procedure is scoped to the current project root, but several triggers such as "context," "scanning," and "exploration" are broad enough that the skill could activate for ordinary requests.

✓ Install Mechanism

The package contains only SKILL.md, no executable payload, declared dependencies, install hooks, or bundled scripts.

ℹ Credentials

Repository-wide scanning is proportionate to the skill purpose, but users should run it only in repositories they intend to summarize because it may reveal project structure and environment variable names in the agent context.

ℹ Persistence & Privilege

No privilege escalation, credential use, network exfiltration, or background persistence is shown; the skill does disclose optional wiki article generation under .codesight/, which can write local files.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install nm-conserve-context-map
安装完成后，直接呼叫该 Skill 的名称或使用 /nm-conserve-context-map 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of nm-conserve-context-map. - Generates a compressed project context map to reduce expensive Read/Grep operations. - Detects project structure, key dependencies, frameworks, entry points, import graph, API routes, hot files, environment variables, middleware, and data models. - Offers command-line options for output format, section selection, token limits, and caching controls. - Produces per-topic wiki articles for selective context loading (.codesight/). - Estimates token savings vs manual code exploration.

元数据

Slug nm-conserve-context-map

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题