git

A set of advanced Git instructions for changing, inspecting, and recovering a project's version history. Git records changes to code so teams can work together and return to earlier states.

In plain words
What is it for?
Use it for interactive rebases, cherry-picking commits, reflog recovery, finding when code changed, checking line history, stashing work, and using multiple worktrees.
Why use it?
It helps when commits need cleaning up, specific changes must be traced, or work appears to have been lost.

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/dineshdb/pie/git
Any agent
npx skills add dineshdb/pie --skill git
Clone the repo
git clone --depth 1 https://github.com/dineshdb/pie

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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 $0.00011 $0.00372
Opus 5 $0.00005 $0.00186
Sonnet 5 $0.00002 $0.00074
Haiku 4.5 $0.00001 $0.00037

Measured yesterday against content hash 9cee9e2ed389, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git 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.

.pie/skills/git/SKILL.md · 45 lines

What it actually says

Advanced Git Operations

Treat history as a document to be groomed for clarity.

1. History Surgery

git rebase -i HEAD~n          # Groom last n commits (squash/edit/drop)
git commit --amend --no-edit  # Add staged changes to last commit
git cherry-pick <hash>        # Apply specific commit to current branch

2. Recovery & Undo

git reflog                    # Find "lost" commits (HEAD history)
git reset --hard HEAD@{n}     # Restore to a specific reflog state
git reset --soft HEAD~1       # Undo commit, keep changes staged
git restore <file>            # Discard local changes

3. Diagnostics & Trace

git log -S "string"           # Find when a string was added/removed (Pickaxe)
git log -L :<func>:<file>      # Evolution of a specific function
git blame -L 10,20 <file>     # Line-level authorship
git show --name-only <hash>   # List files changed in a commit

4. Maintenance

git stash push -m "msg"       # Save dirty state
git stash pop                 # Restore dirty state
git clean -fd                 # Remove untracked files/dirs
git worktree add ../path br   # Work on another branch simultaneously

Principles

  • Atomic Commits: One logical change per commit.
  • Linear History: Prefer rebase over merge for feature updates.
  • Descriptive Messages: Focus on "why" more than "what".
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 · 45 lines · 11 tokens per session scan A 9cee9e2ed389

Subscribe to this mod's changes

git is a skill published in the GitHub repository dineshdb/pie (2 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 372 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

release

Create a new versioned release with changelog. Bumps version in code, updates CHANGELOG.md, commits, tags, and pushes using the repository release flow. GitHub Actions creates the release and uses only the current changelog section as release notes. Use when the user says "release", "cut a release", "bump version"…

genai-io/san · 75 tokens

qa

Regression test a San feature by name. Looks for a feature doc in docs/reference/ or docs/packages/2-feature/, runs automated Go tests and interactive tmux tests, then produces a pass/fail report. Use this skill when the user says "qa", "regression test", "test feature X", "verify feature", or references a feature…

genai-io/san · 85 tokens

openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

KunAgent/Kun · 39 tokens

pi-sync

Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.

sky-valley/pi · 66 tokens

proactive-agent

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.

MerkyorLynn/Lynn · 46 tokens

novel-workshop

小说创作工作台。用户说写小说、创作小说、写故事、写穿越文、写言情、写科幻、创作故事、开始创作、继续写、写下一章、多视角、POV、装订成册时使用。AI-assisted novel writing workbench for outline, characters, chapter drafting, multi-POV narrative, editing, and book assembly.

MerkyorLynn/Lynn · 90 tokens