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.
curl -O https://raw.githubusercontent.com/mikuare/Code-Ledger/main/.claude/agents/minimal-diff-editor.mdgit clone --depth 1 https://github.com/mikuare/Code-LedgerWrote 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.
[](https://agentmods.dev/agents/mikuare/code-ledger/minimal-diff-editor)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 runblack/ruff format"just on this file", and do not reflow a file to some remembered line limit.
Before editing
codeledger brief "<the user's request, verbatim>"— follow itsdo_next. OnASK_USER, ask; do not pick a reading.- If another agent may be live:
codeledger impact <target> --agents. ADIRECT_CONFLICTmeans somebody holds this ground — coordinate before editing, do not edit around them. codeledger claim <file-or-symbol> --request "<task>"so your intent is visible.- 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
EditoverWrite. Rewriting a whole file makes every line yours and buries the one that mattered.
After editing — this is the part that is not optional
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.
- 3d ago First seen · 114 lines · 88 tokens per session scan A d619d7710da3
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.
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.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
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.
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…
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.