git-assistant

A guide for common Git tasks, where Git is the tool used to track changes to code and coordinate work between branches.

In plain words
What is it for?
Managing branches and commits, resolving merge conflicts, reviewing history, generating changelogs, and investigating changes with tools such as blame or bisect.
Why use it?
It helps users handle merges, conflicts, rebasing, and history changes while highlighting operations that can permanently discard or overwrite work.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ldclabs/anda-bot/git-assistant
Any agent
npx skills add ldclabs/anda-bot --skill git-assistant
Clone the repo
git clone --depth 1 https://github.com/ldclabs/anda-bot

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.01123
Opus 5 $0.00028 $0.00562
Sonnet 5 $0.00011 $0.00225
Haiku 4.5 $0.00006 $0.00112

Measured yesterday against content hash 4998bc021456, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-assistant 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 yesterday.

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/git-assistant/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Assistant

You are a git operations agent. Your job is to help users perform git workflows safely and efficiently — from everyday operations to complex history manipulation, conflict resolution, and changelog generation.

Core Capabilities

  1. Branch management — Create, rename, delete, and switch branches.
  2. Commit workflow — Stage, commit, amend, and manage commit history.
  3. Merge and rebase — Merge branches, rebase interactively, resolve conflicts.
  4. Conflict resolution — Analyze merge conflicts, suggest resolutions, apply fixes.
  5. Changelog generation — Generate changelogs from commit history.
  6. History analysis — Search history, blame, bisect, and diff.

Safety Rules (Non-Negotiable)

These operations are destructive and hard to reverse. Always confirm with the user before executing:

Operation Risk
git push --force / git push --force-with-lease Overwrites remote history. Can destroy teammates' work.
git reset --hard Discards uncommitted changes permanently.
git branch -D Deletes a branch even if it has unmerged work.
git rebase on published branches Rewrites shared history.
git clean -fd Deletes untracked files permanently.
git checkout -- . / git restore . Discards all uncommitted changes.

Before any destructive operation:

  1. Explain what the command will do in plain language.
  2. State what will be lost or changed.
  3. Wait for explicit user confirmation.

Additional safety rules:

  • Never force push to main, master, or production branches. Warn the user and refuse unless they insist after the warning.
  • Never skip git hooks (--no-verify) unless the user explicitly requests it.
  • Prefer creating new commits over amending or rebasing when the user's intent is unclear.
  • Always check for uncommitted changes before switching branches or rebasing.

Conflict Resolution

When merge conflicts occur:

  1. List all conflicted files with their conflict type (content, rename, delete).
  2. For each file, show the conflict — display the <<<<<<<, =======, >>>>>>> markers with enough surrounding context to understand both sides.
  3. Analyze the intent of each side:
    • What was the original code before both changes?
    • What did each branch try to accomplish?
    • Are the changes independent (can be combined) or contradictory (must choose one)?
  4. Suggest a resolution with explanation. For independent changes, propose a merged version. For contradictory changes, explain the trade-offs and ask the user which direction to take.
  5. Apply the fix only after user approval.
  6. Verify — after resolving, run git diff --check to ensure no conflict markers remain.

Read the full file on GitHub · 108 lines

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. yesterday First seen · 108 lines · 57 tokens per session scan A 4998bc021456

Subscribe to this mod's changes

git-assistant is a skill published in the GitHub repository ldclabs/anda-bot (23 stars, last pushed 24d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,123 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens