ledger-live: Skill for Claude Code

.agents/skills/run-e2e-ci/SKILL.md

run-e2e-ci is a skill for Claude Code, Codex from LedgerHQ/ledger-live. It costs 71 tokens per session (1,331 once invoked), scanned A, original, MIT.

A workflow trigger for Ledger Wallet's on-demand end-to-end and Coin Tester checks. End-to-end tests run a user flow across the whole app, while Coin Tester checks cryptocurrency-specific behavior.

In plain words
What is it for?
Use it to start desktop or mobile end-to-end tests, or Coin Tester checks, for a branch or pull request. It helps choose filters based on the changed coin, feature, platform, or test flow.
Why use it?
These checks may not run automatically or may be too broad to run every time. The workflow lets you select the smallest relevant set and report the run on a pull request.

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/run-e2e-ci/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 run-e2e-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/ledgerhq/ledger-live/run-e2e-ci.svg)](https://agentmods.dev/skills/ledgerhq/ledger-live/run-e2e-ci)
Your own site
<a href="https://agentmods.dev/skills/ledgerhq/ledger-live/run-e2e-ci"><img src="https://agentmods.dev/badge/skills/ledgerhq/ledger-live/run-e2e-ci.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,331 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 19
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00071 $0.01331
Opus 5 $0.00036 $0.00665
Sonnet 5 $0.00014 $0.00266
Haiku 4.5 $0.00007 $0.00133

Measured 8d ago against content hash 7bf51fa8c05d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

run-e2e-ci 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 8d 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.

.agents/skills/run-e2e-ci/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run E2E / Coin Tester on CI

When: for changes that impact the e2e apps (desktop/mobile/coin logic), once the PR is getting ready for review. Desktop & Mobile E2E only run on a schedule + manual dispatch, so trigger them deliberately. Coin Tester already auto-runs on PRs for affected coins — only dispatch it to force a chain or re-run.

Scope it down first — filtered is the default, full suite is the exception

Always run the smallest subset that covers the change. The full suite is slow, expensive, and competes for shared on-chain accounts, so run it only for genuinely cross-cutting changes — and when you do, say why in the PR comment. Derive the scope from the diff:

What the diff touches How to scope
One coin module (libs/coin-modules/coin-solana) test_filter=@solana + Coin Tester chain=solana
A coin family (**/families/evm) test_filter=@family-evm (or @generic-coin-framework)
A specific spec / flow (swap, subAccount, newSendFlow) test_filter with the tag or spec path
Platform-specific (Android manifest, iOS plist) narrow Mobile tests_type (Android Only / iOS Only); skip the other surfaces
Desktop-only or Mobile-only change run only that surface; skip the others + Coin Tester
Shared / cross-cutting (build tooling, TS upgrade, currency core) full suite — and add a one-line rationale

Filter tags: @bitcoin, @family-evm, @solana, @generic-coin-framework, @smoke, … See the test-filter guide for the grammar and the mobile (whole spec files by path/@-tag) vs desktop (test titles) matching difference.

Dispatch

These are workflow_dispatch workflows — no slash-command triggers them. Dispatch with gh, which must run outside the sandbox (dangerouslyDisableSandbox: true).

gh workflow run --ref <branch> is all you need: the workflows checkout inputs.ref || github.sha, so the optional "Specify branch" (ref) field can stay blank — it falls back to the commit --ref points to. Run-names echo the branch, so use gh run list to confirm.

Read the full file on GitHub · 68 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. 8d ago First seen · 68 lines · 71 tokens per session scan A 7bf51fa8c05d

Subscribe to this mod's changes

run-e2e-ci is a skill published in the GitHub repository LedgerHQ/ledger-live (616 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,331 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 2026-08-30.