Agent skill

Moraine Sandbox QA

by eric-tramel in eric-tramel/moraine

Run isolated Moraine dev sandbox validation. An agent skill from eric-tramel/moraine.

Apache-2.0Auto-check passedDatabases

Install Moraine Sandbox QA

skills CLI
$ npx skills add eric-tramel/moraine --skill moraine-sandbox-qa -a claude-code

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

GitHub CLI
$ gh skill install eric-tramel/moraine moraine-sandbox-qa --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/eric-tramel/moraine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/moraine-dev/skills/moraine-sandbox-qa .claude/skills/moraine-sandbox-qa && 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
moraine-sandbox-qa
GitHub stars
117
Token cost
~668 tokens
SKILL.md length
229 words
Files
2
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run isolated Moraine dev sandbox validation. An agent skill from eric-tramel/moraine.

  • ClickHouse schema
  • SKILL.md covers Overview, When To Use, Boot and Validate, plus 1 more section
  • Calls cargo, bash and curl; needs ANTHROPIC_API_KEY
  • Any change where QA must not touch the developers host ~/.moraine install

What it does

Moraine Sandbox QA is an agent skill from eric-tramel/moraine. Run isolated Moraine dev sandbox validation. Use when testing ingest, MCP, monitor, ClickHouse schema, source formats, stack behavior, or any change where QA must not touch the developer's host ~/.moraine install; use before reporting completion for stack-facing changes.

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Databases, covering Data warehousing and MCP servers. It works with Model Context Protocol and ClickHouse. The repository describes itself as: Unified realtime agent trace database & search MCP. The licence is Apache-2.0.

When your agent uses it

  • ClickHouse schema
  • Any change where QA must not touch the developers host ~/.moraine install
  • Use before reporting completion for stack-facing changes

Example prompts

  • “/moraine-sandbox-qa”

Requirements

  • A credential in ANTHROPIC_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 2fb4aec. 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:

    • cargo
    • bash
    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use curl, 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 these keys or tokens, usually read from environment variables:

    • ANTHROPIC_API_KEY

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

Context cost

Moraine Sandbox QA loads about 668 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 229 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~668

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 eric-tramel/moraine at commit 2fb4aec, republished under its Apache-2.0 licence (© eric-tramel). 229 words, ~668 tokens.

Download SKILL.mdSave it as .claude/skills/moraine-sandbox-qa/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
moraine-sandbox-qa
description
Run isolated Moraine dev sandbox validation. Use when testing ingest, MCP, monitor, ClickHouse schema, source formats, stack behavior, or any change where QA must not touch the developer's host ~/.moraine install; use before reporting completion for stack-facing changes.

Moraine Sandbox QA

Overview

Use the dev sandbox for stack-facing QA so validation runs against an isolated Moraine state directory and sibling ClickHouse service instead of the host install.

When To Use

Use this workflow for changes touching:

  • crates/moraine-ingest-core/, ingest source formats, or fixtures.
  • crates/moraine-mcp-core/, apps/moraine-mcp/, or MCP tool behavior.
  • crates/moraine-monitor-core/, apps/moraine-monitor/, or web/monitor/.
  • sql/, ClickHouse migrations, config templates, or stack lifecycle behavior.
  • Release or smoke-test work that needs end-to-end behavior.

For docs-only or narrow metadata changes, normal local checks are usually enough.

Boot

Boot from the authoritative worktree for the change. Use --quiet; do not pipe moraine-sandbox up through tail or head.

bash
id=$(scripts/dev/sandbox/moraine-sandbox up --quiet)
echo "sandbox: $id"
scripts/dev/sandbox/moraine-sandbox status "$id"

If you spawned from an isolation worktree, compare with the parent or sibling feature worktree first. Boot the sandbox from the worktree that contains the actual in-progress code.

Validate

Use the sandbox shell for cargo and stack checks:

bash
scripts/dev/sandbox/moraine-sandbox shell "$id"
cd /repo
cargo fmt --all -- --check
cargo test -p <crate> --locked
cargo test --workspace --locked
cargo clippy --workspace --all-targets -- -D warnings

Choose focused tests first, then broaden according to risk. For changes that affect ingest, MCP, monitor routes, or schema behavior, run the functional stack smoke test when feasible:

bash
bash scripts/ci/e2e-stack.sh

Check the monitor health endpoint using the sandbox-reported port:

bash
port=$(scripts/dev/sandbox/moraine-sandbox status "$id" | awk -F: '/^\[sandbox\] monitor/{print $NF}')
curl -fsS "http://127.0.0.1:${port}/api/v1/health"

For MCP tool surface changes or release-level confidence, consider scripts/dev/sandbox/agent-smoke-e2e --help. It requires ANTHROPIC_API_KEY.

Teardown

Always tear down the sandbox before reporting the task complete:

bash
scripts/dev/sandbox/moraine-sandbox down "$id"

Final reporting should include the sandbox id, commands run, outcomes, and confirmation that down "$id" succeeded. If sandbox QA was expected but not run, explain why.

© eric-tramel, Apache-2.0. 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 plugins/moraine-dev/skills/moraine-sandbox-qa of eric-tramel/moraine.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 2fb4aec

Compare with similar skills

Moraine Sandbox QA 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.

Moraine Sandbox QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Moraine Sandbox QA this skilleric-tramel/moraine117—~668Automated safety check: PassApache-2.0
Semantic Analystsidequery/sidemantic129—~982Automated safety check: PassAGPL-3.0
Pytorch Clickhousepytorch/test-infra113—~2.8kAutomated safety check: PassCustom licence
Debug Failed Runactivepieces/activepieces25k—~3.7kAutomated safety check: WarnCustom licence
Clickhouse Best Practicesvemetric/vemetric3952 repos~2.6kAutomated safety check: PassApache-2.0
Webapp Buildersidequery/sidemantic129—~5.5kAutomated safety check: PassAGPL-3.0

Similar skills

  • Semantic Analyst

    sidequery/sidemantic

    Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer.

    129 GitHub stars~982 tokensUpdated 3 days ago
    DatabasesAuto-check passed
  • Pytorch Clickhouse

    pytorch/test-infra

    Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.

    113 GitHub stars~2.8k tokensUpdated today
    DatabasesAuto-check passed
  • Debug Failed Run

    activepieces/activepieces

    Debug a failed Activepieces flow run end-to-end: given a flow run id (or BullMQ job id), find why it failed, cross-referencing the live BullMQ job + Postgres rows (SSH script on the DevOps box), the…

    25k GitHub stars~3.7k tokensUpdated today
    DatabasesAuto-check: warnings
  • Clickhouse Best Practices

    vemetric/vemetric

    MUST USE when reviewing ClickHouse schemas, queries, or configurations.

    395 GitHub starsUsed in 2 repos~2.6k tokens
    DatabasesAuto-check passed
  • Webapp Builder

    sidequery/sidemantic

    Build interactive analytics webapps, demos, dashboards, or embedded app surfaces from Sidemantic semantic models using copyable component primitives and deterministic query inspection.

    129 GitHub stars~5.5k tokensUpdated 3 days ago
    DatabasesAuto-check passed
  • Release

    hypequery/hypequery

    Cut a stable hypequery release via Changesets, or explain/check the canary flow.

    103 GitHub stars~623 tokensUpdated yesterday
    DatabasesAuto-check passed

More from eric-tramel/moraine

All 19 skills in this repo
  • Moraine Release Publisher

    eric-tramel/moraine

    Cuts and publishes a Moraine release end to end: version bump PR, tag, GitHub release notes, workflow check and PyPI package verification.

    117 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Moraine Release Notes

    eric-tramel/moraine

    Rewrites a moraine GitHub release body into a usage-focused format with install block, what's new, platform table, upgrade notes and one deduplicated changelog.

    117 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Multi-Persona Code Review

    eric-tramel/moraine

    Coordinates a delegated review of a Moraine PR or local change by seven focused reviewer subagents, merges their findings and follows up on the fixes.

    117 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Elegance-Focused Code Review

    eric-tramel/moraine

    Looks at a pull request for the smallest good design, hunting for simplifications and architectural moves that remove whole classes of problems.

    117 GitHub stars~473 tokensUpdated today
    Auto-check passed
  • Idiomatic Code Review

    eric-tramel/moraine

    Reviews a pull request for idiomatic implementation: use of the language, standard library, ecosystem conventions and the repository's own patterns.

    117 GitHub stars~469 tokensUpdated today
    Auto-check passed
  • Code Review Security Review

    eric-tramel/moraine

    Review a PR through the CodeReviewSecurityReview persona. An agent skill from eric-tramel/moraine.

    117 GitHub stars~497 tokensUpdated today
    Auto-check passed

Categories

Questions about Moraine Sandbox QA

What does Moraine Sandbox QA do?

Run isolated Moraine dev sandbox validation. An agent skill from eric-tramel/moraine. Moraine Sandbox QA is an agent skill from eric-tramel/moraine. Run isolated Moraine dev sandbox validation.

When should I use Moraine Sandbox QA?

Moraine Sandbox QA fits situations like: clickHouse schema; any change where QA must not touch the developers host ~/.moraine install; use before reporting completion for stack-facing changes.

How do I install Moraine Sandbox QA in Claude Code?

Run `npx skills add eric-tramel/moraine --skill moraine-sandbox-qa -a claude-code`. Or copy the skill folder (plugins/moraine-dev/skills/moraine-sandbox-qa in eric-tramel/moraine) into .claude/skills/moraine-sandbox-qa in your project. Claude Code loads it when a task matches its description.

How do I install Moraine Sandbox QA in Codex?

Run `npx skills add eric-tramel/moraine --skill moraine-sandbox-qa -a codex`. Or copy the skill folder (plugins/moraine-dev/skills/moraine-sandbox-qa in eric-tramel/moraine) into .agents/skills/moraine-sandbox-qa in your project. Codex loads it when a task matches its description.

Can I use Moraine Sandbox QA 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 eric-tramel/moraine --skill moraine-sandbox-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moraine-sandbox-qa, .gemini/skills/moraine-sandbox-qa, .github/skills/moraine-sandbox-qa and .opencode/skills/moraine-sandbox-qa in your project.

What does Moraine Sandbox QA need to run?

Going by SKILL.md and its folder, Moraine Sandbox QA needs the command-line tools its instructions call (cargo, bash and curl) and credentials named ANTHROPIC_API_KEY. Our summary lists: A credential in ANTHROPIC_API_KEY.

Does Moraine Sandbox QA access the network?

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

Is Moraine Sandbox QA 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 Moraine Sandbox QA use?

Moraine Sandbox QA is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Moraine Sandbox QA use?

About 668 tokens (SKILL.md is roughly 2.7k 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 Moraine Sandbox QA?

Skills that share tags, products or a category with Moraine Sandbox QA: Semantic Analyst (sidequery/sidemantic, 129 stars), Pytorch Clickhouse (pytorch/test-infra, 113 stars), Debug Failed Run (activepieces/activepieces, 25k stars) and Clickhouse Best Practices (vemetric/vemetric, 395 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Moraine Sandbox QA?

eric-tramel (a GitHub user) maintains it in eric-tramel/moraine, which has 117 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 5, 2026.

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