ledger-commit

ledger-commit is a command for Claude Code from nunoamorim99/agile-ledger. It costs 18 tokens per session (357 once invoked), scanned A, original, MIT.

A command for reviewing and committing changes in the central Agile-Ledger repository. It groups changes by repository, proposes commit messages based on the actual diff, and can push only after confirmation.

In plain words
What is it for?
Use it to inspect status and diffs, prepare one commit per changed group, commit after confirmation, and optionally push the ledger repository.
Why use it?
It keeps planning changes out of the code repository and reduces the risk of committing an inaccurate summary or pushing without approval. It also prevents rewriting ledger history.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agile-ledger plugin — 2 skills, 34 commands shipped together

Good fit Use it to inspect status and diffs, prepare one commit per changed group, commit after confirmation, and optionally push the ledger repository.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/nunoamorim99/agile-ledger/ledger-commit
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.

Clone the repo
git clone --depth 1 https://github.com/nunoamorim99/agile-ledger

Made for: Claude Code.

Or install agile-ledger, the plugin that ships this one along with the rest of its 2 skills, 34 commands.

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-commit

README.md
[![agentmods](https://agentmods.dev/badge/commands/nunoamorim99/agile-ledger/ledger-commit/github.svg)](https://agentmods.dev/commands/nunoamorim99/agile-ledger/ledger-commit)
Your own site
<a href="https://agentmods.dev/commands/nunoamorim99/agile-ledger/ledger-commit"><img src="https://agentmods.dev/badge/commands/nunoamorim99/agile-ledger/ledger-commit/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-commit

Your own site · 80×15
<a href="https://agentmods.dev/commands/nunoamorim99/agile-ledger/ledger-commit"><img src="https://agentmods.dev/badge/commands/nunoamorim99/agile-ledger/ledger-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 357 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 $0.00018 $0.00357
Opus 5.5 $0.00007 $0.00143
Sonnet 5.5 $0.00004 $0.00071
Haiku 4.5 $0.00002 $0.00036

Measured 3d ago against content hash ba5e7891e7a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ledger-commit 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.

plugins/agile-ledger/commands/ledger-commit.md · 15 lines

What it actually says

Using the Agile-Ledger Workspace skill, commit the pending changes in the ledger repo (never the code repo).

  1. Show git status and git diff --stat for the ledger root, grouped by repo folder, plus the ledger-root files (Registry.md, Config.md) as their own group.
  2. Propose one commit message per group, describing what actually changed — ledger(repo-a): US-014 → Done (sprint 7), ledger(repo-b): triage 3 ideas → EPIC-007, ledger: register repo-c. Read the diff to write the message; never guess from the command history.
  3. Commit on confirmation, one commit per group, on ledger_branch.
  4. Push only if ledger_push is confirm and the user confirms this push. Never force-push, never rewrite ledger history, never open a PR.

If the ledger root is not the cwd, a git -C <ledger-root> ... call falls outside the whitelisted plain forms and will ask for approval once — expected, not a reason to skip the commit.

If the working tree is clean, say so and stop. This is the manual counterpart to ledger_commit: confirm in Config.md, and the way to tidy up after a session run with ledger_commit: off.

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 · 15 lines · 18 tokens per session scan A ba5e7891e7a2

Subscribe to this mod's changes

ledger-commit is a command published in the GitHub repository nunoamorim99/agile-ledger (1 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 357 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.