commit-context

Agent Skills › rohitg00/agentmemory › commit-context

commit-context

GitHub

追踪代码变更对应的 Agent 会话上下文。当用户询问代码来源、修改原因或特定位置背景时使用，通过 git 命令获取 SHA 并查询关联的 Agent 会话及观察记录，严禁臆测无记录的意图。

plugin/skills/commit-context/SKILL.md rohitg00/agentmemory

Trigger Scenarios

用户询问'这段代码为什么在这里' 用户想知道'这个文件/函数是谁写的'或'Agent 在此时做了什么' 需要查看代码库中特定位置的上下文信息

Install

npx skills add rohitg00/agentmemory --skill commit-context -g -y

More Options

Non-standard path

npx skills add https://github.com/rohitg00/agentmemory/tree/main/plugin/skills/commit-context -g -y

Use without installing

npx skills use rohitg00/agentmemory@commit-context

指定 Agent (Claude Code)

npx skills add rohitg00/agentmemory --skill commit-context -a claude-code -g -y

安装 repo 全部 skill

npx skills add rohitg00/agentmemory --all -g -y

预览 repo 内 skill

npx skills add rohitg00/agentmemory --list

SKILL.md

Frontmatter

{
    "name": "commit-context",
    "description": "Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks \"why is this code here\", \"what was the agent doing when this changed\", \"who wrote this\", or wants context on a specific location in the codebase.",
    "argument-hint": "[file, function, or line]",
    "user-invocable": true
}

The user wants commit context for: $ARGUMENTS

Quick start

git blame -L 40,52 src/auth/refresh.ts   # -> SHA 9a1b2c3d

memory_commit_lookup { "sha": "9a1b2c3d4e5f60718293a4b5c6d7e8f901234567" }

Expected output:

9a1b2c3 on main by dev: "rotate refresh tokens"
Linked session 7f3a9c2 "Auth refresh rework", 14 obs.

Why

Report only what git and the lookup return. When the lookup gives commit: null, the commit predates session linking; do not invent intent.

Workflow

Find the SHA: git blame -L <start>,<end> <file> for a line range; git log -L :<function>:<file> for a function; git log -n 1 -- <file> for a bare path.
Look it up: memory_commit_lookup { "sha": "<full-sha>" }.
Present the commit (sha, short sha, branch, author, message), the linked session(s) (id, project, started/ended, observation count, summary), and the importance >= 7 observations via memory_recall when available.