agent-tests

agent-tests is a skill for Claude Code, Codex from dylanroscover/Embody. It costs 56 tokens per session (1,465 once invoked), scanned B, original, MIT.

A guide for running tests that use real AI clients, such as Claude Code and Codex, to check an MCP connection from start to finish.

In plain words
What is it for?
Use it when checking that AI clients can connect to Envoy's MCP tools, complete a handshake, see the expected tools, and perform selected calls.
Why use it?
These tests can use paid AI subscription capacity, so running them accidentally is costly. The guide keeps them separate from normal test runs and explains how to run them safely.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dylanroscover/embody/agent-tests
Any agent
npx skills add dylanroscover/Embody --skill agent-tests
Clone the repo
git clone --depth 1 https://github.com/dylanroscover/Embody

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 agent-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/dylanroscover/embody/agent-tests.svg)](https://agentmods.dev/skills/dylanroscover/embody/agent-tests)
Your own site
<a href="https://agentmods.dev/skills/dylanroscover/embody/agent-tests"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/agent-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,465 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00056 $0.01465
Opus 5 $0.00028 $0.00732
Sonnet 5 $0.00011 $0.00293
Haiku 4.5 $0.00006 $0.00146

Measured 5d ago against content hash 5001c371c7e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agent-tests scanned grade B 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`.mcp.json`; the user's `~/.codex/config.toml` is never touched), with
.claude/skills/agent-tests/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Tier Tests (AI-client connectivity)

The AGENT tier verifies that real AI clients -- Claude Code, Codex, and a deterministic MCP contract client -- can reach and correctly use Envoy's MCP tools end to end. Like destructive-tests.md, this is a dev-only convention for the Embody test harness -- it has NO shipped template counterpart.

The tier model

  • Suites inherit AgentTestCase (which carries AGENT = True). They are EXCLUDED from RunTests / RunTestsSync / RunTestsDeferred* AND from RunDestructiveTests by _discoverTestSuites' tier filter. Do not remove that guard: a normal full run must never spawn AI clients or burn subscription usage silently.
  • They run ONLY via op.unit_tests.RunAgentTests(suite_name=None, test_name=None, delay_frames=30) -- fire-and-forget; poll GetResults().
  • Two layers:
    • Tier 1 (test_agent_contract): no LLM. An out-of-process stdlib MCP client (agent_clients/mcp_contract_client.py) spawns the EXACT bridge command from .mcp.json and checks handshake, tool inventory vs the EXPECTED_ENVOY_TOOLS manifest, and a curated call sequence. This is the cheap, deterministic half -- run it first when diagnosing.
    • Tier 2 (test_agent_smoke_claude / test_agent_smoke_codex): a real agent on scripted micro-tasks, verified against LIVE TD state (probe op exists with the exact run token), never the agent's prose alone.

Why the runner is async (do not "simplify" it)

Envoy drains MCP requests on TD's MAIN thread (max 5 per frame). A test that blocks the main thread while an agent subprocess makes MCP calls deadlocks the very tools under test until every call times out. So RunAgentTests launches subprocesses non-blocking (stdout/stderr to temp FILES -- an unread PIPE deadlocks the child at ~64KB; stdin always DEVNULL -- codex exec hangs probing a silent stdin pipe on Windows, openai/codex#20919) and polls them via a run(delayFrames=N) chain using the STRING-EXPRESSION form, so a mid-run extension reinit cannot strand the state machine on a stale instance. Timeouts kill the whole process TREE (the CLIs spawn the bridge as a child).

Read the full file on GitHub · 105 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. 5d ago First seen · 105 lines · 56 tokens per session scan B 5001c371c7e3

Subscribe to this mod's changes

agent-tests is a skill published in the GitHub repository dylanroscover/Embody (169 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,465 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

n8n-agents

Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…

czlonkowski/n8n-mcp · 156 tokens

agentcore-investigation

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.

awslabs/mcp · 52 tokens

amazon aurora dsql

Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.

awslabs/mcp · 46 tokens

resolve-pr-comments-stack

Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack.…

maximhq/bifrost · 99 tokens

split-commit-into-stack

Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…

maximhq/bifrost · 96 tokens

resolve-pr-comments

Skill "resolve-pr-comments" from maximhq/bifrost, covering resolve pr comments, usage, workflow overview, step 1: detect repository and step 2: fetch unresolved comments (graphql).

maximhq/bifrost · 0 tokens