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.
npx skills add michael-denyer/memory-mcp --skill test-memorygit clone --depth 1 https://github.com/michael-denyer/memory-mcpWrote 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/michael-denyer/memory-mcp/test-memory)<a href="https://agentmods.dev/skills/michael-denyer/memory-mcp/test-memory"><img src="https://agentmods.dev/badge/skills/michael-denyer/memory-mcp/test-memory/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/michael-denyer/memory-mcp/test-memory"><img src="https://agentmods.dev/badge/skills/michael-denyer/memory-mcp/test-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.03564 |
| Opus 5.5 | $0.00005 | $0.01426 |
| Sonnet 5.5 | $0.00002 | $0.00713 |
| Haiku 4.5 | $0.00001 | $0.00356 |
Grade A, and why
test-memory 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory MCP Live Testing Skill
Run /test-memory to start a guided testing session. Walk through each phase, execute tests, and track results.
Prerequisites
Install memory-mcp from the marketplace:
# Add the marketplace
/plugin marketplace add michael-denyer/memory-mcp
# Install the plugin
/plugin install memory-mcp@michael-denyer/memory-mcp
Or install directly:
/plugin install github:michael-denyer/memory-mcp
Phases
Phase 1: Core Memory Operations
1.1 Remember - Store test memories:
remember("Test: FastAPI with async endpoints", memory_type="project", tags=["test", "tech-stack"])
remember("Test: Always use uv run pytest -v", memory_type="pattern", tags=["test", "commands"])
remember("Test: API rate limit 100 req/min", memory_type="reference", tags=["test", "api"])
Record the returned IDs for later tests.
1.2 Recall - Semantic search (use different phrasings):
- "what framework for backend" → should find FastAPI
- "how to run tests" → should find pytest
- "request throttling" → should find rate limit
Verify confidence levels returned.
1.3 Recall Modes - Compare precision vs exploratory:
recall("testing", mode="precision")→ fewer, higher-confidencerecall("testing", mode="exploratory")→ more results
1.4 Recall by Tag:
recall_by_tag("test")→ should return all test memories
1.5 Forget - Delete one test memory and verify it's gone.
Phase 2: Hot Cache Mechanics
2.1 Manual Promotion:
promote(memory_id)one of the test memorieshot_cache_status()→ verify it appears
2.2 Manual Demotion:
demote(memory_id)- Verify removed from hot cache but still recallable
2.3 Pin/Unpin:
pin(memory_id)→ pinned_count increasesunpin(memory_id)→ pinned_count decreases
2.4 Auto-Promotion (optional - requires multiple recalls):
- Create a memory and recall it 3+ times
- Check if auto-promoted
Phase 3: Knowledge Graph
3.1 Create Linked Memories:
remember("Test: Database uses PostgreSQL") → ID: A
remember("Test: pgvector for embeddings") → ID: B
remember("Test: Vector search needs pgvector") → ID: C
link_memories(A, B, "relates_to")
link_memories(B, C, "depends_on")
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.
- 1mo ago Changed 47e22ff5ff29
- 1mo ago First seen · 440 lines · 12 tokens per session scan A 7dbb3c8d4ccc
test-memory is a skill published in the GitHub repository michael-denyer/memory-mcp (12 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 3,564 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other skills, from other repositories
lore-onboard
First-time setup wizard for LoreConvo. Verifies the MCP server is connected, the database is accessible, hooks are configured, and runs a test save/load cycle. Use when the user says "set up loreconvo", "onboard", "/lore-onboard", "verify loreconvo", "test loreconvo setup", or after first installing the plugin.
codspeed-optimize
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…
emulate-seed
Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS, Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs — full state machines, not mocks. Use when setting up test environments, CI pipelines, integration tests…
architecture-patterns
Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.