ledger-live: Skill for Claude Code

.agents/skills/create-changeset/SKILL.md

create-changeset is a skill for Claude Code, Codex from LedgerHQ/ledger-live. It costs 45 tokens per session (642 once invoked), scanned A, original, MIT.

A release-note file generator for the Ledger Live monorepo. A monorepo is one repository containing multiple related applications and libraries.

In plain words
What is it for?
It creates a changeset with the affected package, the release impact level, and a short description of the change.
Why use it?
It helps record package changes in the format used by the Changesets release tool, reducing mistakes when preparing a pull request or release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is LedgerHQ/ledger-live's own configuration. It tells Claude Code and Codex how to work on ledger-live 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-live configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LedgerHQ/ledger-live. 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/LedgerHQ/ledger-live/develop/.agents/skills/create-changeset/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LedgerHQ/ledger-live

Made for: Claude Code, Codex.

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 create-changeset

README.md
[![agentmods](https://agentmods.dev/badge/skills/ledgerhq/ledger-live/create-changeset/github.svg)](https://agentmods.dev/skills/ledgerhq/ledger-live/create-changeset)
Your own site
<a href="https://agentmods.dev/skills/ledgerhq/ledger-live/create-changeset"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/create-changeset/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 create-changeset

Your own site · 80×15
<a href="https://agentmods.dev/skills/ledgerhq/ledger-live/create-changeset"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/create-changeset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 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 $0.00045 $0.00642
Opus 5.5 $0.00018 $0.00257
Sonnet 5.5 $0.00009 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured yesterday against content hash 1b3a7288ee81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-changeset 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 yesterday.

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.

.agents/skills/create-changeset/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Changeset

Create a .changeset/<adjective-noun-verb>.md file (human-readable random identifier, matching @changesets/cli convention) with this format:

---
"package-name": minor
---

Short description of the change

Package Names

Package names must match exactly what's in each package.json:

App / Lib Package name
Mobile app live-mobile
Desktop app ledger-live-desktop
Common lib @ledgerhq/live-common
Coin modules @ledgerhq/coin-<name> (e.g. @ledgerhq/coin-sui)
Layer packages @shared/<name>, @domain/entity-<name>, @domain/api-<name>, @features/flow-<name>, @features/platform-<name>, @devtools/<name> (e.g. @domain/entity-contact, @features/flow-contacts)
Other libs Check the lib's package.json name field

Private and published packages

  • Layer packages are private. Every package under shared/, domain/, features/, devtools/ and support/ has "private": true and is never published to npm. .changeset/config.json sets privatePackages.version: true and tag: false: a changeset still bumps a private package's version and writes its CHANGELOG.md, but publishes and tags nothing. Name the changed layer packages in the changeset like any other package, together with the app (ledger-live-desktop, live-mobile) whose users see the change.
  • No changeset for development-only changes. A change that only touches support/ presets or devDependencies needs none, and neither do docs and skills.
  • Published packages are the @ledgerhq/* packages without "private": true in their package.json, almost all under libs/. Their changeset becomes an npm release.

Impact Levels

Level When to use
minor The minimum: new features, bug fixes, internal changes
major Breaking changes (rare, requires discussion)
patch Only in a PR based on a hotfix branch, never on develop

Read the full file on GitHub · 53 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. yesterday Changed · +7 lines 1b3a7288ee81
  2. 2mo ago First seen · 46 lines · 45 tokens per session scan A f53a1776ecf4

Subscribe to this mod's changes

create-changeset is a skill published in the GitHub repository LedgerHQ/ledger-live (624 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 642 once invoked, about $0.0002 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 2026-08-30.