Agent skill

E2E Coverage

by LanternOps in LanternOps/breeze

A skill your agent uses when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness…

AGPL-3.0Auto-check passedTesting & QA

Install E2E Coverage

skills CLI
$ npx skills add LanternOps/breeze --skill e2e-coverage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LanternOps/breeze e2e-coverage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/e2e-coverage .claude/skills/e2e-coverage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
e2e-coverage
GitHub stars
130
Token cost
~1.6k tokens
SKILL.md length
704 words
Files
2
Skills in repo
14
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness…

  • Works in 6 steps: Baseline. git tag --sort=-creatordate |… → Delta + carry-forward. git log ..HEAD… → Verify/bring up env. Step 0 above —… → …
  • Running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs
  • SKILL.md covers Overview, The trap that costs the most…, The efficiency loop and The coverage ledger, plus 2 more sections
  • Calls git

What it does

E2E Coverage is an agent skill from LanternOps/breeze. Use when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness sweeps, or resuming a partial sweep. Tracks coverage across runs so each sweep only tests the delta. NOT for single-feature post-implementation checks (use feature-testing for that).

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `runbook.md`).

It sits in Testing & QA, covering End-to-end testing and Feature launches and release readiness. The repository describes itself as: The open-source IT platform that comes with the workers. RMM + PSA in one system, with a governed AI operator built in. The licence is AGPL-3.0.

When your agent uses it

  • Running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs
  • Commits — test everything since the last release
  • Release-readiness sweeps
  • Resuming a partial sweep

Example prompts

  • “test everything since the last release”
  • “/e2e-coverage”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Baseline. git tag --sort=-creatordate | head → last released tag. Find the most recent docs/testing/*-test-results.md and its "last swept…
  2. Delta + carry-forward. git log ..HEAD --oneline. Open the previous results file and carry forward every item still marked DEFERRED /…
  3. Verify/bring up env. Step 0 above — confirm the live stack serves HEAD, then bring up only what's missing. All breeze-specific recipes are…
  4. Classify each delta commit/PR using the legend below. Map each to the layer(s) that can prove it, and mark whether it needs external…
  5. Test the delta. Reuse runbook.md recipes (login/JWT, RBAC negative tests, device lookups) and feature-testing's per-layer mechanics…
  6. Record. Write/update the two ledger files and the index pointer (below).

What it can do on your machine

Read from SKILL.md and the folder at commit 1f72bb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

E2E Coverage loads about 1.6k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LanternOps/breeze at commit 1f72bb7, republished under its AGPL-3.0 licence (© LanternOps). 704 words, ~1,604 tokens.

Download SKILL.mdSave it as .claude/skills/e2e-coverage/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
e2e-coverage
description
Use when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness sweeps, or resuming a partial sweep. Tracks coverage across runs so each sweep only tests the delta. NOT for single-feature post-implementation checks (use feature-testing for that).

E2E Coverage Sweep

Overview

A coverage sweep verifies everything that changed since a baseline (a release tag or the last sweep), live, across UI/API/agent layers — and records what passed, failed, or was deferred so the next sweep is cheaper.

Core principle: every sweep starts from the last sweep. You test the delta (new commits + previously-deferred items), reuse a known-good environment recipe, and write results back to a durable ledger. Efficiency compounds: the env setup is recorded once, and covered ground is never re-tested.

For single-feature post-implementation verification, use the feature-testing skill instead — this skill is for broad multi-PR passes and reuses feature-testing's per-layer mechanics.

The trap that costs the most time

The running containers may NOT be running the code you think they are. A checked-out branch does not mean the live stack serves it — the containers can be an old image, a detached build, or a stale dist/. Testing against the wrong build produces false PASSes and phantom 404s.

Always verify the live stack before testing anything. See runbook.md → "Verify the stack is running the code under test". This is step 0 of every sweep.

The efficiency loop

dot
digraph sweep {
  rankdir=TB;
  baseline [label="1. Baseline = max(last release tag, last swept commit)", shape=box];
  delta    [label="2. Delta = git log baseline..HEAD + carry-forward unresolved items", shape=box];
  env      [label="3. Verify/bring up env (runbook.md) — confirm it serves HEAD", shape=box];
  classify [label="4. Classify each item: P0/P1/P2 x API/UI/AGENT/SKIP, creds-free vs creds-gated", shape=box];
  test     [label="5. Test the delta (reuse runbook recipes); record as you go", shape=box];
  record   [label="6. Write plan + results files; update the index pointer", shape=box];
  baseline -> delta -> env -> classify -> test -> record;
}
  1. Baseline. git tag --sort=-creatordate | head → last released tag. Find the most recent docs/testing/*-test-results.md and its "last swept commit". Baseline = whichever is newer. If no prior sweep, baseline = the last release tag.
  2. Delta + carry-forward. git log <baseline>..HEAD --oneline. Open the previous results file and carry forward every item still marked DEFERRED / NEEDS-CREDS / open FAIL — recheck whether creds/agents are now available. Items marked PASS below the baseline are not re-tested.
  3. Verify/bring up env. Step 0 above — confirm the live stack serves HEAD, then bring up only what's missing. All breeze-specific recipes are in runbook.md. Don't rediscover them.
  4. Classify each delta commit/PR using the legend below. Map each to the layer(s) that can prove it, and mark whether it needs external credentials or a live agent (defer those explicitly — never silently drop them).
  5. Test the delta. Reuse runbook.md recipes (login/JWT, RBAC negative tests, device lookups) and feature-testing's per-layer mechanics. Record each result immediately.
  6. Record. Write/update the two ledger files and the index pointer (below).
Show full SKILL.md (348 more words)Show less

The coverage ledger

Two files per sweep in docs/testing/, plus one living index. Keep the existing format (see docs/testing/v0.66.1-to-HEAD-*.md as the reference shape).

FilePurpose
docs/testing/<baseline>-to-HEAD-test-plan.mdThe classified checklist of delta items (one per PR/commit), P0/P1/P2 + layer tags
docs/testing/<baseline>-to-HEAD-test-results.mdResults: per-item status + evidence, findings, bugs filed. Records the "last swept commit".
docs/testing/e2e-coverage-index.mdOne line per sweep: baseline → results file → last-swept commit. The pointer the next sweep reads first.

Status legend (use these exact tokens so the next sweep can grep them):

  • PASS — verified live, with evidence.
  • FAIL — broken; file/track a bug, link it. Stays carried-forward until fixed+reverified.
  • DEFERRED — testable but not exercised this run (time/data); say why.
  • NEEDS-CREDS — blocked on external credentials or a live agent (Google/M365 tenant, Win/macOS agent). Carried forward.
  • SKIP — covered by unit/CI; no manual E2E warranted (dep bumps, internal refactors). Note it; don't silently omit.

Priority legend: P0 = security / auth / multi-tenant isolation / data corruption. P1 = user-visible new feature or behavior change. P2 = secondary surface or pre-existing area touched.

Quick reference

NeedCommand / pointer
Last release taggit tag --sort=-creatordate | head
Delta since baselinegit log <baseline>..HEAD --oneline
Is the live stack serving HEAD?runbook.md → stale-stack verification
Bring up local env (caddy + dev mode)runbook.md → bring-up
Local login → JWTrunbook.md → JWT helper (admin@breeze.local / BreezeAdmin123!)
RBAC negative testsrunbook.md → site-scoped e2e-sitea user
Seed topology (orgs/sites/devices)runbook.md → seed topology
curl fails inside a loop?runbook.md → sandbox gotcha (use /usr/bin/curl, no loops)

Common mistakes

  • Testing against a stale stack. The #1 false-PASS source. Verify the live build serves HEAD before anything (runbook step 0).
  • Re-testing covered ground. Read the previous results file first; only test the delta + carried-forward items.
  • Silently dropping creds-gated items. Mark NEEDS-CREDS and carry forward — don't let them vanish from coverage.
  • Using the prod E2E_* env creds locally. Those target 2breeze.app (often down). Local DB uses admin@breeze.local / BreezeAdmin123! — see runbook.
  • Trusting a single-org admin to catch tenant bugs. The seed partner admin is multi-org on purpose; org-resolution bugs only surface with multi-org/multi-site users (runbook → seed topology).
  • Forgetting to write results back. The ledger is the efficiency engine. No results file = next sweep redoes your work.

© LanternOps, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .claude/skills/e2e-coverage of LanternOps/breeze.

  • SKILL.md
  • runbook.md

Open the folder on GitHubat commit 1f72bb7

Compare with similar skills

E2E Coverage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

E2E Coverage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
E2E Coverage this skillLanternOps/breeze130—~1.6kAutomated safety check: PassAGPL-3.0
Solo Maintainer Releaseserithemage/serverless-openclaw196—~418Automated safety check: PassNone
Releasecodewhale-hq/Codewhale41k—~189Automated safety check: PassMIT
Test Scenariosphuryn/pm-skills27k—~866Automated safety check: PassMIT
Hai Goalhylarucoder/hai-stack380—~2kAutomated safety check: PassCustom licence
Qe Courtproffesor-for-testing/agentic-qe494—~3.2kAutomated safety check: PassMIT

Similar skills

  • Solo Maintainer Release

    serithemage/serverless-openclaw

    Runs solo-maintainer release work end-to-end: release readiness review, notes, tags, GitHub release creation, deploy workflow dispatch, and post-release verification.

    196 GitHub stars~418 tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Release

    codewhale-hq/Codewhale

    Prepare a named version: preflight, version consistency, build/package, smoke test, checksums/notes, and release readiness.

    41k GitHub stars~189 tokensUpdated today
    Testing & QAAuto-check passed
  • Test Scenarios

    phuryn/pm-skills

    Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes.

    27k GitHub stars~866 tokensUpdated 22 days ago
    Testing & QAAuto-check passed
  • Hai Goal

    hylarucoder/hai-stack

    Creates or rewrites a goal document for ambiguous, multi-phase, high-risk, or explicitly planned execution: verifiable outcome, boundary, current state, phases, proof-bearing todos, dry-run, and…

    380 GitHub stars~2k tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • Qe Court

    proffesor-for-testing/agentic-qe

    Adversarial review court — a delivery (diff, PR, test suite, or artifact) is prosecuted by independent AI reviewers from different vendors, each with its own probe set, then a SHIP verdict must…

    494 GitHub stars~3.2k tokensUpdated 3 days ago
    Testing & QAAuto-check passed
  • Test Planning

    petrkindlmann/qa-skills

    Build a single sprint or release test plan. An agent skill from petrkindlmann/qa-skills.

    163 GitHub stars~4.2k tokensUpdated 3 mo ago
    Testing & QAAuto-check passed

More from LanternOps/breeze

All 14 skills in this repo
  • Agent Info

    LanternOps/breeze

    Quick reference for the Breeze RMM Go agent architecture, commands, configuration, build process, and data flows.

    130 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes
  • Agent Log Debugging

    LanternOps/breeze

    A skill your agent uses when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs.

    130 GitHub stars~1.6k tokensUpdated today
    Auto-check: notes
  • AI Agent

    LanternOps/breeze

    Quick reference for the Breeze RMM AI Agent system architecture, MCP tools, streaming chat, cost tracking, guardrails, and MCP server.

    130 GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Breeze Helper

    LanternOps/breeze

    Quick reference for the Breeze Helper Tauri desktop app — architecture, Rust backend commands, React frontend, config files, IPC with the Go agent, helper chat API routes, tool approval flow, and…

    130 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Feature Delivery

    LanternOps/breeze

    A skill your agent uses when orchestrating Breeze implementation work from this seat — dispatching waves or issue fixes to background sessions, deciding whether an open PR gets merged, handling a…

    130 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Gh Queue

    LanternOps/breeze

    A skill your agent uses when reviewing, triaging, or managing the incoming GitHub backlog on the Breeze repo — PRs, Discussions, AND Issues.

    130 GitHub stars~5k tokensUpdated today
    Auto-check passed

Questions about E2E Coverage

What does E2E Coverage do?

A skill your agent uses when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness…. E2E Coverage is an agent skill from LanternOps/breeze. Use when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness sweeps, or resuming a partial sweep.

When should I use E2E Coverage?

E2E Coverage fits situations like: running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs; commits — test everything since the last release; release-readiness sweeps; resuming a partial sweep.

How do I install E2E Coverage in Claude Code?

Run `npx skills add LanternOps/breeze --skill e2e-coverage -a claude-code`. Or copy the skill folder (.claude/skills/e2e-coverage in LanternOps/breeze) into .claude/skills/e2e-coverage in your project. Claude Code loads it when a task matches its description.

How do I install E2E Coverage in Codex?

Run `npx skills add LanternOps/breeze --skill e2e-coverage -a codex`. Or copy the skill folder (.claude/skills/e2e-coverage in LanternOps/breeze) into .agents/skills/e2e-coverage in your project. Codex loads it when a task matches its description.

Can I use E2E Coverage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LanternOps/breeze --skill e2e-coverage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/e2e-coverage, .gemini/skills/e2e-coverage, .github/skills/e2e-coverage and .opencode/skills/e2e-coverage in your project.

What does E2E Coverage need to run?

Going by SKILL.md and its folder, E2E Coverage needs the command-line tools its instructions call (git).

Does E2E Coverage access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is E2E Coverage safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does E2E Coverage use?

E2E Coverage is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does E2E Coverage use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to E2E Coverage?

Skills that share tags, products or a category with E2E Coverage: Solo Maintainer Release (serithemage/serverless-openclaw, 196 stars), Release (codewhale-hq/Codewhale, 41k stars), Test Scenarios (phuryn/pm-skills, 27k stars) and Hai Goal (hylarucoder/hai-stack, 380 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains E2E Coverage?

LanternOps (a GitHub organization) maintains it in LanternOps/breeze, which has 130 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

Source: LanternOps/breeze on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.