ledger: Agent for Claude Code

.claude/agents/ledger-reviewer.md

ledger-reviewer is an agent for Claude Code from eternal-roman/ledger. It costs 36 tokens per session (344 once invoked), scanned A, original, MIT.

A strict code reviewer for software that handles money, accounts, and financial records. It checks accounting rules, precision, security, citations, determinism, and tests.

In plain words
What is it for?
Use it during pull-request or pre-commit review of monetary changes, especially code using double-entry accounting.
Why use it?
It helps catch incorrect amounts, unbalanced transactions, precision loss, unsupported assumptions, and other serious financial-code defects before merging.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is eternal-roman/ledger's own configuration. It tells Claude Code how to work on 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 ledger configures →

Part of the ledger plugin — 8 skills, 4 commands, 1 agent, 1 hook, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to eternal-roman/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/eternal-roman/ledger/main/.claude/agents/ledger-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/eternal-roman/ledger

Made for: Claude Code.

Or install ledger, the plugin that ships this one along with the rest of its 8 skills, 4 commands, 1 agent, 1 hook, 1 MCP server.

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 ledger-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eternal-roman/ledger/ledger-reviewer/github.svg)](https://agentmods.dev/agents/eternal-roman/ledger/ledger-reviewer)
Your own site
<a href="https://agentmods.dev/agents/eternal-roman/ledger/ledger-reviewer"><img src="https://agentmods.dev/badge/agents/eternal-roman/ledger/ledger-reviewer/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 ledger-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/eternal-roman/ledger/ledger-reviewer"><img src="https://agentmods.dev/badge/agents/eternal-roman/ledger/ledger-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00036 $0.00344
Opus 5 $0.00018 $0.00172
Sonnet 5 $0.00007 $0.00069
Haiku 4.5 $0.00004 $0.00034

Measured 9d ago against content hash d6170770a779, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ledger-reviewer 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 9d 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/ledger-reviewer.md · 33 lines

What it actually says

You review monetary code against the Ledger kernel. Canon, Zero-Skip, deterministic.

Act as a financial auditor and code reviewer.

Non-negotiable Requirements

  • Every monetary amount must use Money.from(...) from 'ledger' or 'ledger/core'. Flag native numbers or floats immediately.
  • All value movement must go through JournalEntry + validateEntry + Ledger.apply (no mutation).
  • The accounting equation and double-entry balance must be proven in the change or comments.
  • Any rate, date, jurisdiction, or policy assumption must have a citation (use /ledger-cite or knowledge graph if available).
  • Determinism and reproducibility must be clear.

Additional Layers (leverage available plugins)

  • Run or simulate silent-failure-hunter logic on error handling and edge calculations.
  • Type design: strong encapsulation and invariants on core types.
  • Tests: demand coverage for the new financial paths (pr-test-analyzer mindset).
  • Security: no opportunities for amount tampering, precision loss on input, or bad serialization.

Output

Structure findings by severity:

  • CRITICAL (must fix before merge): any invariant violation
  • HIGH: missing citations or weak tests
  • MEDIUM: clarity / simplification opportunities (after invariants are solid)

End with: "Ledger review: PASS / FAIL (with summary)."

Reference AGENTS.md, CLAUDE.md, and skills/ledger* for the full doctrine. Never approve unbalanced or unproven financial code.

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. 9d ago First seen · 33 lines · 36 tokens per session scan A d6170770a779

Subscribe to this mod's changes

ledger-reviewer is an agent published in the GitHub repository eternal-roman/ledger (1 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 344 once invoked, about $0.0002 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.