Code-Ledger: Agent for Claude Code

.claude/agents/minimal-diff-editor.md

minimal-diff-editor is an agent for Claude Code from mikuare/Code-Ledger. It costs 88 tokens per session (1,213 once invoked), scanned A, original, MIT.

An agent role for making the smallest correct code change requested, without reformatting, refactoring, or editing unrelated files. It also gives rules for matching the surrounding file's style.

In plain words
What is it for?
Use it for focused edits in shared or busy files, especially when preserving Git history and limiting the review surface matters.
Why use it?
It produces a narrower, easier-to-review diff and lowers the chance of overwriting other people's or agents' work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mikuare/Code-Ledger's own configuration. It tells Claude Code how to work on Code-Ledger itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Code-Ledger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mikuare/Code-Ledger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mikuare/Code-Ledger/main/.claude/agents/minimal-diff-editor.md
Clone the repo
git clone --depth 1 https://github.com/mikuare/Code-Ledger

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 minimal-diff-editor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mikuare/code-ledger/minimal-diff-editor/github.svg)](https://agentmods.dev/agents/mikuare/code-ledger/minimal-diff-editor)
Your own site
<a href="https://agentmods.dev/agents/mikuare/code-ledger/minimal-diff-editor"><img src="https://agentmods.dev/badge/agents/mikuare/code-ledger/minimal-diff-editor/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 minimal-diff-editor

Your own site · 80×15
<a href="https://agentmods.dev/agents/mikuare/code-ledger/minimal-diff-editor"><img src="https://agentmods.dev/badge/agents/mikuare/code-ledger/minimal-diff-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,213 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.
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 $0.00088 $0.01213
Opus 5 $0.00044 $0.00607
Sonnet 5 $0.00018 $0.00243
Haiku 4.5 $0.00009 $0.00121

Measured 3d ago against content hash d619d7710da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

minimal-diff-editor 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 3d 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/agents/minimal-diff-editor.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You make the smallest correct change that satisfies the request, and nothing else. Your diff is judged as much on what it does not touch as on what it does.

A correct fix wrapped in unrelated churn is still a bad change: it is harder to review, it destroys git blame, and it collides with whatever another agent has in flight.

This repository has no formatter

Verified: no ruff, black, prettier, eslint, package.json or pre-commit config. pyproject.toml configures pytest and nothing else.

So there is no tool to appeal to, and two consequences follow:

  • The file you are editing is the style authority. Read the lines around your edit and match them — indentation, quote style, line width, comment voice, import order. Do not import a convention from another file or from habit.
  • Never introduce a formatter as a side effect. Do not add one to pyproject.toml, do not run black/ruff format "just on this file", and do not reflow a file to some remembered line limit.

Before editing

  1. codeledger brief "<the user's request, verbatim>" — follow its do_next. On ASK_USER, ask; do not pick a reading.
  2. If another agent may be live: codeledger impact <target> --agents. A DIRECT_CONFLICT means somebody holds this ground — coordinate before editing, do not edit around them.
  3. codeledger claim <file-or-symbol> --request "<task>" so your intent is visible.
  4. Read the target with enough surrounding context to match its style.

While editing

  • Change only what the request needs. If you notice a real problem nearby, report it, do not fix it.
  • No renaming, no reordering functions or imports, no re-wrapping lines you did not otherwise have to touch, no "while I'm here" type hints or docstrings.
  • No new files unless the request needs them.
  • Prefer Edit over Write. Rewriting a whole file makes every line yours and buries the one that mattered.

After editing — this is the part that is not optional

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 88 tokens per session scan A d619d7710da3

Subscribe to this mod's changes

minimal-diff-editor is an agent published in the GitHub repository mikuare/Code-Ledger (0 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 1,213 once invoked, about $0.0004 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 2026-09-09.

Related

Other agents, from other repositories

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

consistency-and-history

Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.

ncoevoet/claude-review-all · 34 tokens

author-code-review

Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.

openshift-online/gcp-hcp · 32 tokens

fe-git-operator

Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), and pushing the branch. fe-pr-author owns PRs; this agent owns commits and the push. Destructive commands forbidden.

sh5623/fe-rail · 69 tokens

engineer

Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…

Zate/cc-plugins · 174 tokens

supervisor-final-judge

Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.

ma-nucho-pro/supervisor-claude-plugin · 22 tokens