prepare-commit-changes

A workflow for selecting individual Git changes, called hunks, and staging only the ones the user approves for a commit.

In plain words
What is it for?
Listing staged and unstaged hunks, presenting them for selection, and adding the chosen hunks to Git’s staging area.
Why use it?
It prevents unrelated edits from being included together and keeps the user in control of what enters the staging area.

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/awish021/opencode/prepare-commit-changes
Any agent
npx skills add Awish021/opencode --skill prepare-commit-changes
Clone the repo
git clone --depth 1 https://github.com/Awish021/opencode

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 617 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 $0.00019 $0.00617
Opus 5 $0.00010 $0.00309
Sonnet 5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured 2d ago against content hash e32567230e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prepare-commit-changes 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 2d 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/prepare-commit-changes/SKILL.md · 75 lines

What it actually says

Prepare Commit Changes

What I do

  • List all unstaged and staged hunks with their unique IDs
  • Present hunks to the user for selection
  • Stage only the hunks the user explicitly selects

When to use this

Use this when the user asks to stage changes to git.

Hunk ID Format

file:@-old,len+new,len - derived from diff @@ headers, stable across reordering

Commands

  • git hunks list - List all unstaged hunks with unique IDs
  • git hunks list --staged - List already staged hunks
  • git hunks add <hunk-id> [<hunk-id> ...] - Stage specific hunks by their ID

Workflow

  1. Run git hunks list to show all unstaged hunks
  2. Run git hunks list --staged to show already staged hunks
  3. Present both lists to the user with numbered options
  4. Ask the user to select hunks to stage (accepts multiple: comma-separated, ranges, or all keyword)
  5. Run git hunks add with all selected hunk IDs
  6. Confirm which hunks were staged

Guardrails

  • Only stage hunks the user explicitly selects
  • Never assume which hunks to stage without user confirmation
  • Allow multi-hunk selection in a single prompt
  • If selection is empty, stage nothing
  • Show both unstaged and staged hunks so user knows current state

Examples

List hunks and stage selected ones:

$ git hunks list
1. src/main.c:@-10,6+10,7
2. src/utils.c:@-25,3+25,4
3. tests/api.test.js:@-50,10+50,12

$ git hunks list --staged
A. src/config.c:@-5,2+5,3

Select hunks to stage (e.g., "1,3" or "1-2" or "all"): 1,3

$ git hunks add 'src/main.c:@-10,6+10,7' 'tests/api.test.js:@-50,10+50,12'
Staged: src/main.c:@-10,6+10,7, tests/api.test.js:@-50,10+50,12

Stage from already staged hunks:

$ git hunks list --staged
1. src/auth.c:@-100,5+100,6

Select hunks to stage (or press Enter to skip): 1

$ git hunks add 'src/auth.c:@-100,5+100,6'
Staged: src/auth.c:@-100,5+100,6
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. 2d ago First seen · 75 lines · 19 tokens per session scan A e32567230e38

Subscribe to this mod's changes

prepare-commit-changes is a skill published in the GitHub repository Awish021/opencode (11 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 617 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 2026-08-30.

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