agentleFS
jellydnjellydn/my-ai-tools/skills/git-context/SKILL.md

git-context

Skill127 starsChanged 26 days agoMITView on GitHub

Search git history for context — commit messages, blame, related changes, impact analysis

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 14
  2. Distinctive:

    Before implementing a change, check:

    line 106
  3. Distinctive:

    Commit messages matter: Write clear messages — they become the primary documentation

    line 139
  4. Very specific:

    Use --all for complete picture: Default git log only shows current branch history

    line 143
  5. Very specific:

    Use before /blindspots to gather initial context

    line 147
  6. Very specific:

    Use during context-discovery for deep git history analysis

    line 148

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Git Context

When to Use

Use this skill when:

  • Understanding why code was written a certain way
  • Finding related changes across the codebase
  • Tracing the evolution of a feature or pattern
  • Identifying who has expertise in a module
  • Finding past bug fixes or regressions in an area

What It Does

Searches git history to build context about the codebase, using a combination of native git commands and the sem MCP tool for deeper analysis. Helps answer "why was this done this way?" and "what changed recently in this area?"

How to Execute

Find Recent Changes to a Module

# Recent commits touching this area
git log --oneline --all -20 -- path/to/module/

# Who works on this area most
git shortlog -sn -- path/to/module/

# When a specific function was introduced
git log -S "functionName" --oneline -- path/to/module/

Trace a Function's History

# When was this function introduced?
git log -S "export function calculateTotal" --oneline

# Who has modified it?
git blame path/to/file.ts -L 10,30

# What was the commit message?
git show <commit-hash> --no-patch

Find Related Changes

# Files changed together in the same commits
git log --all --name-only -- path/to/changed/file.ts | head -20

# Find commits that reference a ticket or pattern
git log --all --grep="fix|bug|hotfix" --oneline -20

Using sem for Deeper Analysis

# Entity-level blame (function level)
sem blame path/to/file.ts --function processOrder

# Impact analysis
sem impact path/to/file.ts --function processOrder

# Compare branches at function level
sem diff main..HEAD -- path/to/file.ts

Cross-Session Context

# Search past agent sessions about this module
ctx search "this module" path/to/module/

# Find past discussions about related changes
ctx search "bug fix" path/to/module/

Decision Tree

┌────────────────────────────┬────────────────────────┐
│ Need this                   │ Use this               │
├────────────────────────────┼────────────────────────┤
│ What changed recently      │ git log -20 -- path/   │
│ Who works on this module   │ git shortlog -sn path/ │
│ Why was this line added    │ git blame path/to/file │
│ When was function added    │ git log -S "funcName"  │
│ What else changed together │ git log --name-only    │
│ Impact of changing X       │ sem impact path/func   │
│ Past agent work on this    │ ctx search "topic"     │
└────────────────────────────┴────────────────────────┘

Common Patterns

Pre-Implementation Check

Before implementing a change, check:

# 1. Recent changes to affected modules
git log --oneline --all -10 -- src/feature/

# 2. Who has expertise
git shortlog -sn -- src/feature/ | head -5

# 3. Related commits (ticket/branch references)
git log --all --grep="feature-name" --oneline

# 4. Past bugs in this area
git log --all --grep="bug|fix|error" --oneline -10 -- src/feature/

Post-Change Verification

After implementing, verify:

# 1. What did I change?
git diff --stat

# 2. Are there unrelated changes?
git diff --cached --name-only

# 3. Did I miss anything?
git diff HEAD --name-only  # Unstaged changes

Tips

  • Commit messages matter: Write clear messages — they become the primary documentation
  • Use git log -S over grep for history: grep scans the working tree; git log -S scans history
  • Combine with ctx: Past agent sessions often contain context that git history doesn't
  • Be specific with paths: git log -- path/ filters to relevant commits, reducing noise
  • Use --all for complete picture: Default git log only shows current branch history

Integration with Other Skills

  • Use before /blindspots to gather initial context
  • Use during context-discovery for deep git history analysis
  • Log surprising git history findings in implementation-logger

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.