agent-plugin-smoke-test

A smoke test for checking that an Agent Plugin loaded in Pi, a coding-agent environment, and that its bundled test server is reachable. It verifies the skill, the connection to the Model Context Protocol server, and two simple test operations.

In plain words
What is it for?
Use it after installing or changing an Agent Plugin to test skill discovery, MCP connectivity, an echo operation, and addition of 20 plus 22. It reports each check as passed or failed and gives a reload instruction when Pi started before the configuration existed.
Why use it?
It quickly separates a missing skill, an uninitialized configuration, and a failed tool connection. That makes plugin installation and trust problems easier to diagnose.

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/blockedpath/pi-agent-plugins/agent-plugin-smoke-test
Any agent
npx skills add BlockedPath/pi-agent-plugins --skill agent-plugin-smoke-test
Clone the repo
git clone --depth 1 https://github.com/BlockedPath/pi-agent-plugins

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 409 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.00409
Opus 5 $0.00025 $0.00204
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 2d ago against content hash 662784af8550, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-plugin-smoke-test 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 2d 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.

examples/pi-agent-plugins-smoke/skills/agent-plugin-smoke-test/SKILL.md · 51 lines

What it actually says

Agent Plugin smoke test

Use this workflow to verify both portable component types.

1. Confirm skill loading

Tell the user: Agent Skill loaded successfully.

2. Confirm MCP discovery

Use the mcp gateway to list the server named pi-agent-plugins-smoke__everything:

mcp({ server: "pi-agent-plugins-smoke__everything" })

If MCP reports 0/0 servers, the current Pi session initialized before the generated config existed. Ask the user to run Pi's built-in /reload command (or restart Pi), then retry once. For other failures, inspect MCP status and report the exact startup error. The first launch can take longer because npx downloads the official @modelcontextprotocol/server-everything package.

3. Call real MCP tools

From the returned tool list:

  1. Call the server's echo tool with Agent Plugin MCP works.
  2. Call its add tool with a = 20 and b = 22.
  3. Verify that echo returns the same text and add returns 42.

Use the exact tool names returned by the MCP gateway rather than guessing their host prefixes.

4. Report

Return a concise result:

Skill: PASS
MCP connection: PASS
Echo: PASS
Add (20 + 22 = 42): PASS

For any failure, replace PASS with FAIL and include the exact error.

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. 2d ago First seen · 51 lines · 50 tokens per session scan A 662784af8550

Subscribe to this mod's changes

agent-plugin-smoke-test is a skill published in the GitHub repository BlockedPath/pi-agent-plugins (5 stars, last pushed 26d ago), licensed MIT. It adds 50 tokens to every session and 409 once invoked, about $0.0003 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 2026-08-31.