Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/eric-tramel/morainenpx agentmods add skills/eric-tramel/moraine/moraine-sandbox-qaWrote 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/moraine-sandbox-qa)<a href="https://agentmods.dev/skills/eric-tramel/moraine/moraine-sandbox-qa"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/moraine-sandbox-qa/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.
<a href="https://agentmods.dev/skills/eric-tramel/moraine/moraine-sandbox-qa"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/moraine-sandbox-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00633 |
| Opus 5 | $0.00030 | $0.00316 |
| Sonnet 5 | $0.00012 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
moraine-sandbox-qa scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS "http://127.0.0.1:${port}/api/v1/health" How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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/, orweb/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.
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:
scripts/dev/sandbox/moraine-sandbox shell "$id"
cd /repo
cargo fmt --all -- --check
cargo test -p <crate> --locked
cargo test --workspace --locked
cargo clippy --workspace --all-targets -- -D warnings
Choose focused tests first, then broaden according to risk. For changes that affect ingest, MCP, monitor routes, or schema behavior, run the functional stack smoke test when feasible:
bash scripts/ci/e2e-stack.sh
Check the monitor health endpoint using the sandbox-reported port:
port=$(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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 73 lines · 60 tokens per session scan A a6437ee8618e
moraine-sandbox-qa is a skill published in the GitHub repository eric-tramel/moraine (117 stars, last pushed 25d ago), licensed Apache-2.0. It adds 60 tokens to every session and 633 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
web3-testing
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.