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 agentmods add skills/dojogenesis/mcp/memory-gardennpx skills add DojoGenesis/mcp --skill memory-gardengit clone --depth 1 https://github.com/DojoGenesis/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/dojogenesis/mcp/memory-garden)<a href="https://agentmods.dev/skills/dojogenesis/mcp/memory-garden"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/memory-garden.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.03238 |
| Opus 5 | $0.00034 | $0.01619 |
| Sonnet 5 | $0.00013 | $0.00648 |
| Haiku 4.5 | $0.00007 | $0.00324 |
Grade A, and why
memory-garden 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 4d 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Garden
Version: 1.1 Author: Tres Pies Design Purpose: Write structured, semantically rich memory entries for efficient context management using a three-tier hierarchy and growth semantics.
I. Philosophy: Memory is a Garden, Not a Landfill
Memory should be cultivated, not accumulated. A garden requires tending -- planting what matters, composting what doesn't, and harvesting wisdom when it's ripe. The three-tier hierarchy ensures that raw experiences are refined into lasting wisdom, and that context windows remain fertile ground for new thinking rather than overgrown thickets of old data.
Growth language is not decoration -- it's a thinking tool. When we say "plant" instead of "create," we prime ourselves to consider whether this seed will actually grow. When we say "compost" instead of "delete," we acknowledge that even released material contributed to the soil.
The 3-month rule is the gardener's pruning shears: if it won't matter in 3 months, it doesn't deserve permanent cultivation.
II. When to Use This Skill
- Writing a daily note after a session or workday
- Deciding where an artifact belongs in the three-tier hierarchy
- Compressing Tier A notes into Tier B wisdom or Tier C archives
- Running a garden health check to identify stale or overgrown areas
- Onboarding someone to the memory garden structure
- Choosing what to cultivate vs. compost from a long session
When NOT to use: If the content is a one-time reference (API docs, config values) that doesn't evolve, it's documentation, not a garden artifact. If it's a reusable pattern, it's a seed -- use the seed-extraction skill.
III. The Three-Tier Hierarchy
Tier A: Raw Daily Notes
Purpose: Capture everything from today's session
Lifespan: 1-3 days before compression
Location: notes/YYYY-MM-DD_daily.md
Template sections:
- Key Activities (2-3 bullets)
- Decisions Made (with rationale)
- Seeds Discovered (with trigger)
- Open Questions (to carry forward)
- Tomorrow's Growth (next steps)
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.
- 4d ago First seen · 481 lines · 67 tokens per session scan A 1fa7b704a066
memory-garden is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 3,238 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.
Other skills, from other repositories
memory-index
Index a folder's contents into the MemPalace semantic memory for search and retrieval. Use this skill whenever the user asks to "index a folder", "index a directory", "index memory", "mine a project into memory", "make a folder searchable", "embed a folder", "ingest code into the palace", or "index this directory for…
memory-mine
Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.
memory-status
Show MemPalace memory system status — drawer counts, wings, rooms, knowledge graph stats, and embedding model state.
cobra-viper
Expert skill for building CLI applications with Cobra and Viper, authored by spf13 — the original creator of both libraries. Covers command-first architecture, decoupled business logic, configuration management, environment variable binding, context-aware commands, and in-memory CLI testing. Use whenever a Go CLI or…
notebrain-assistant
Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like…
cartographer-ops
Configure, operate, troubleshoot, or upgrade a Cartographer server or client; connect agents and manage Knowledge Bases.