granular-git

granular-git is a skill for Claude Code, Codex from definite-d/agent-skills. It costs 121 tokens per session (767 once invoked), scanned A, original, MIT.

A Git workflow for staging and committing only exact parts of file changes while leaving the files on disk unchanged.

In plain words
What is it for?
Use it to commit one logical change, stage character-level edits, or add a new file without modifying the working copy.
Why use it?
It prevents unrelated or unfinished edits from being included in a commit and preserves existing staged 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/definite-d/agent-skills/granular-git
Any agent
npx skills add definite-d/agent-skills --skill granular-git
Clone the repo
git clone --depth 1 https://github.com/definite-d/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for granular-git

README.md
[![agentmods](https://agentmods.dev/badge/skills/definite-d/agent-skills/granular-git.svg)](https://agentmods.dev/skills/definite-d/agent-skills/granular-git)
Your own site
<a href="https://agentmods.dev/skills/definite-d/agent-skills/granular-git"><img src="https://agentmods.dev/badge/skills/definite-d/agent-skills/granular-git.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 767 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 $0.00121 $0.00767
Opus 5 $0.00060 $0.00383
Sonnet 5 $0.00024 $0.00153
Haiku 4.5 $0.00012 $0.00077

Measured 4d ago against content hash 16c117c14cd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

granular-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 4d ago.

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/granular-git/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Granular Git

Stage and commit exact file content without touching the working directory.

Core Concept

Standard Git: Working Directory → Staging Area → Commit

This skill reverses the flow: the agent constructs the exact desired file state in memory and injects it directly into the Staging Area.

[Target State] → hash-object → update-index → commit

The physical file on disk is never modified.

Procedure

1. Determine Target State

Read current index state if there are existing staged changes to preserve:

git show :0:path/to/file.txt

Apply character-level edits to that string (not the disk file).

2. Write as Git Object

TARGET_SHA=$(printf '%s' "$TARGET_CONTENT" | git hash-object -w --stdin)

3. Map to Index

For tracked files:

git update-index --cacheinfo 100644,"$TARGET_SHA","path/to/file.txt"

For brand-new files:

git update-index --add --cacheinfo 100644,"$TARGET_SHA","path/to/file.txt"
Argument When
--add Required for untracked files
100644 Regular files
100755 Executable files

4. Commit

git commit -m "type(scope): description"

Multi-Commit Pattern

For multiple independent changes in one file:

HEAD → Commit 1 (Change A) → Commit 2 (A+B) → Commit 3 (A+B+C)
  1. Construct target state for Change A only
  2. Commit
  3. Add Change B to target state, commit
  4. Repeat for Change C

Safety Checklist

  • Is Git initialized? — git rev-parse --is-inside-work-tree
  • Existing staged changes? — Read via git show :0:<file> and merge
  • Repo in clean state? — No ongoing merge/rebase

Advantages Over Patches

Property Patches This Skill
Context sensitivity Fails if context changed Immune
Precision Line-level Character-level
Working directory May modify Never touches

Example

File on disk has Bug fix + Refactor + Docs. You want to commit only the bug fix:

Read the full file on GitHub · 110 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 110 lines · 121 tokens per session scan A 16c117c14cd7

Subscribe to this mod's changes

granular-git is a skill published in the GitHub repository definite-d/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 767 once invoked, about $0.0006 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.