fresh-eyes-amend

fresh-eyes-amend is a skill for Claude Code from jackfranklin/dotfiles. It costs 52 tokens per session (832 once invoked), scanned A, original, MIT.

A workflow for adding current changes to the previous Git commit and having two independent reviewers examine the combined diff. Git is a tool for tracking code changes, and a commit is a saved snapshot of those changes.

In plain words
What is it for?
Use it when amending the previous commit and choosing an accurate final commit message. It checks the working state, stages needed changes, reviews the full diff, and combines the reviewers' suggestions.
Why use it?
It helps catch incomplete or misleading commit messages after more work has been added to an existing commit. Independent reviews reduce the chance that the latest changes are judged only from the author's perspective.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Good fit Use it when amending the previous commit and choosing an accurate final commit message. It checks the working state, stages needed changes, reviews the full diff, and combines the reviewers' suggestions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jackfranklin/dotfiles/fresh-eyes-amend
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.

Any agent
npx skills add jackfranklin/dotfiles --skill fresh-eyes-amend
Clone the repo
git clone --depth 1 https://github.com/jackfranklin/dotfiles

Made for: Claude Code.

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 fresh-eyes-amend

README.md
[![agentmods](https://agentmods.dev/badge/skills/jackfranklin/dotfiles/fresh-eyes-amend/github.svg)](https://agentmods.dev/skills/jackfranklin/dotfiles/fresh-eyes-amend)
Your own site
<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/fresh-eyes-amend"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/fresh-eyes-amend/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fresh-eyes-amend

Your own site · 80×15
<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/fresh-eyes-amend"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/fresh-eyes-amend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00052 $0.00832
Opus 5 $0.00026 $0.00416
Sonnet 5 $0.00010 $0.00166
Haiku 4.5 $0.00005 $0.00083

Measured 11d ago against content hash 07d98af45836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fresh-eyes-amend 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 11d 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.

claude/skills/fresh-eyes-amend/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fresh Eyes Amend

Use this skill when you want to amend the previous commit and ensure the commit message accurately and unbiasedly reflects the entire combined change.

Workflow

  1. Check Status and Stage Changes: Run git status --porcelain to check for active, unstaged changes. If and only if there are changes to be staged, stage them using appropriate git add commands (e.g., git add -u or git add <file>). Avoid blindly running git add -A unless you intend to include all modified and untracked files in the commit. If there are no changes to stage, proceed to the next step.

  2. Capture Old Message: Retrieve and save the current commit message:

    git log -1 --pretty=%B
    

    Keep this as OLD_MESSAGE.

  3. Capture Full Diff: Get the complete diff of the staged changes (and current HEAD) against the parent of HEAD:

    git diff --cached HEAD~1
    

    Keep this as FULL_DIFF.

  4. Spawn Subagents with Zero Context: Invoke two parallel subagents using the invoke_subagent tool. Both subagents must receive the identical FULL_DIFF and be instructed to evaluate it with zero prior context.

    • Subagent 1 (FreshEyesReviewer1):
      • Role: Fresh Eyes Reviewer A
      • Prompt:
        You are a fresh-eyes code reviewer. Your only source of information is the git diff provided below. Do not use any other tools to explore the codebase or check git history. Write a high-quality commit message (following standard guidelines: imperative mood, clear summary, explanation of "why" and "how" in the body) that accurately and completely summarizes the changes in this diff. Do not assume any context outside of what is visible in the diff.
        
        CRITICAL: Do NOT include trivial, inane, or self-evident details in the message body (e.g., "added unit tests", "fixed lint errors", "updated imports", "formatted code", "updated build files"). Focus exclusively on the logical "why" and "how" of the change.
        
        Diff:
        <FULL_DIFF>
        
    • Subagent 2 (FreshEyesReviewer2):
      • Role: Fresh Eyes Reviewer B
      • Prompt: Use the exact same prompt as Subagent 1.

Read the full file on GitHub · 60 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. 11d ago First seen · 60 lines · 52 tokens per session scan A 07d98af45836

Subscribe to this mod's changes

fresh-eyes-amend is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 832 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.