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-curatornpx skills add DojoGenesis/mcp --skill memory-curatorgit 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-curator)<a href="https://agentmods.dev/skills/dojogenesis/mcp/memory-curator"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/memory-curator.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 | $0.00034 | $0.00632 |
| Opus 5 | $0.00017 | $0.00316 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
memory-curator 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.
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 Curator
Manages the persistent memory system — writes, updates, prunes, and deduplicates memories while keeping the MEMORY.md index lean and navigable.
Workflow
1. SCAN
Read MEMORY.md index and all referenced memory files in the memory directory. Build an inventory of:
- Total memory count
- Categories represented
- Line count of MEMORY.md (warn if approaching 200-line limit)
- Any orphaned files (not referenced in index) or broken links (referenced but missing)
2. DEDUP
Detect semantically duplicate memories — same fact stored with different wording. Criteria:
- Same file paths or function names referenced
- Same decision recorded with different timestamps
- Same feedback captured in multiple sessions Flag duplicates for merge, never auto-delete.
3. STALE
Identify memories referencing things that no longer exist:
- File paths that return 404
- Function/variable names not found in codebase
- Project states that have been superseded (e.g., "in progress" when actually shipped)
- Version numbers that are outdated
4. MERGE
Combine related memories that cover the same topic:
- Two user-profile memories → single comprehensive profile
- Multiple feedback entries about the same convention → one authoritative entry
- Project memories tracking the same initiative at different points → latest state only Preserve the most specific, actionable content from each source.
5. PRUNE
Remove memories that are:
- Derivable from current code (architecture that's obvious from reading the source)
- Stale beyond repair (references entirely removed codebases or abandoned projects)
- Duplicated after merge step Never prune: user preferences, feedback corrections, reference pointers to external systems.
6. INDEX
Rebuild MEMORY.md:
- One line per entry, under 150 characters
- Grouped by semantic category (User, Feedback, Project, Reference, Seeds, etc.)
- Most-referenced memories near the top of each group
- Total line count must stay under 200
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.
- 3d ago First seen · 75 lines · 34 tokens per session scan A 715b75ae9de4
memory-curator is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 632 once invoked, about $0.0002 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.