Borrowing it
Nothing to install: this file belongs to eric-tramel/moraine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/eric-tramel/moraine/main/.claude/skills/agent-smoke-e2e/SKILL.mdgit clone --depth 1 https://github.com/eric-tramel/moraineWrote 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.
[](https://agentmods.dev/skills/eric-tramel/moraine/agent-smoke-e2e)<a href="https://agentmods.dev/skills/eric-tramel/moraine/agent-smoke-e2e"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/agent-smoke-e2e.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
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 Excessive Agency · line 19 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.01935 |
| Opus 5 | $0.00019 | $0.00967 |
| Sonnet 5 | $0.00008 | $0.00387 |
| Haiku 4.5 | $0.00004 | $0.00194 |
Grade A, and why
agent-smoke-e2e 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.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-smoke-e2e
You are running an end-to-end smoke test of the moraine MCP server.
Your sole job is to call the public MCP retrieval workflow, validate that responses are shaped as expected, and emit a final pass/fail matrix. Do not do anything else: no exploration, no reading files, no code changes. Treat this like a test runner with terse output and clear pass/fail signals.
Setup Assumptions
- The
moraineMCP server is registered and exposesmcp__moraine__search_sessions,mcp__moraine__open,mcp__moraine__list_sessions, andmcp__moraine__file_attention. - The stack may or may not have ingested sessions. Both cases are valid; the smoke test cares that tools respond with the contract shape.
- Do not call any tool outside the
mcp__moraine__*namespace.
Test Sequence
Run each check below in order. For each check, call the tool with the arguments listed, inspect the response, then record PASS or FAIL with a one-line reason on FAIL.
1. search_sessions
Call mcp__moraine__search_sessions with:
{ "query": "moraine", "n_hits": 5 }
PASS if the response is an object with:
tool: "search_sessions"schema_version: "moraine.mcp.search_sessions.v1"data.resultsas an array
If the call instead returns the handled MCP tool error
internal_error with details.reason: "read_model_refresh" and
details.retryable: true, retry once. If the retry returns the same handled
error, record PASS active ingest is publishing; this is the documented
freshness contract, not an MCP/RPC failure.
If data.results[0] exists, capture:
sample_event_id = data.results[0].open.event_idsample_turn_id = data.results[0].open.turn_idsample_session_id = data.results[0].open.session_id
If there are no results, leave the three sample IDs as null.
2. list_sessions
Call mcp__moraine__list_sessions with:
{
"start_datetime": "1970-01-01T00:00:00Z",
"end_datetime": "2100-01-01T00:00:00Z",
"limit": 5
}
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.
- 8d ago First seen · 235 lines · 38 tokens per session scan A 94b717ed3b3b
agent-smoke-e2e is a skill published in the GitHub repository eric-tramel/moraine (117 stars, last pushed 22d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,935 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 2026-08-30.
Other skills, from other repositories
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
pod-e2e
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Runs end-to-end tests (backend API + frontend Playwright) for a Kiro Crew feature worktree against an ISOLATED throwaway pod…
android-emulator
Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…