test-all

test-all is a command for Claude Code from michael-denyer/memory-mcp. It costs 9 tokens per session (732 once invoked), scanned A, original, MIT.

An interactive command for testing all features of Memory MCP, a system that stores and retrieves information for an AI agent. It offers a full test, a selected phase, or a quick smoke test, meaning a short basic health check.

In plain words
What is it for?
Use it to run the complete 12-phase test, test one area, or perform a quick check of core memory operations.
Why use it?
It gives you a guided way to check whether memory storage, search, relationships, trust handling, sessions, and maintenance work correctly.

Command for Claude Code

Part of the memory-mcp plugin — 3 skills, 14 commands, 1 agent, 1 MCP server shipped together

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 commands/michael-denyer/memory-mcp/test-all
Clone the repo
git clone --depth 1 https://github.com/michael-denyer/memory-mcp

Made for: Claude Code.

Or install memory-mcp, the plugin that ships this one along with the rest of its 3 skills, 14 commands, 1 agent, 1 MCP server.

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 test-all

README.md
[![agentmods](https://agentmods.dev/badge/commands/michael-denyer/memory-mcp/test-all.svg)](https://agentmods.dev/commands/michael-denyer/memory-mcp/test-all)
Your own site
<a href="https://agentmods.dev/commands/michael-denyer/memory-mcp/test-all"><img src="https://agentmods.dev/badge/commands/michael-denyer/memory-mcp/test-all.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 732 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 $0.00009 $0.00732
Opus 5 $0.00005 $0.00366
Sonnet 5 $0.00002 $0.00146
Haiku 4.5 $0.00001 $0.00073

Measured 3d ago against content hash 689bac36af87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-all 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 3d 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.

.claude-plugin/commands/test-all.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory MCP Live Testing

Run /memory-mcp:test-all to start a guided testing session. Walk through each phase, execute tests, and track results.

Execution Modes

Ask user which approach:

  1. Full suite - Run all 12 phases sequentially with pauses between
  2. Specific phase - Run just one phase (1-12)
  3. Smoke test - Quick 2-minute sanity check

Quick Smoke Test

For a 2-minute sanity check:

mcp__memory__remember("Smoke test", tags=["smoke"])  # → get ID
mcp__memory__recall("smoke")
mcp__memory__promote(id)
mcp__memory__hot_cache_status()
mcp__memory__demote(id)
mcp__memory__forget(id)
mcp__memory__memory_stats()

Test Phases

Phase Name Tests
1 Core Operations remember, recall, forget
2 Hot Cache promote, demote, pin, unpin
3 Knowledge Graph link, unlink, traverse
4-5 Trust & Contradictions validate, invalidate, resolve
6 Sessions episodic memory, summarize
7 Mining log_output, run_mining, approve
8 Seeding seed_from_text, bootstrap
9-10 Predictive & Quality predict_next, mark_used
11 Maintenance db_info, cleanup, consolidate
12 Resources hot-cache, working-set
14 Edge Cases error handling
15 Cleanup remove test data

Test Tracking

Track results as you go:

Phase Status Notes
1. Core
2. Hot Cache
3. Graph
4-5. Trust
6. Sessions
7. Mining
8. Seeding
9-10. Predictive
11. Maintenance
12. Resources
14. Edge Cases
15. Cleanup

Read the full file on GitHub · 75 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. 3d ago First seen · 75 lines · 9 tokens per session scan A 689bac36af87

Subscribe to this mod's changes

test-all is a command published in the GitHub repository michael-denyer/memory-mcp (7 stars, last pushed 15d ago), licensed MIT. It adds 9 tokens to every session and 732 once invoked, about $0.0000 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.