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 commands/kid-sid/claude-spellbook/mem_savegit clone --depth 1 https://github.com/kid-sid/claude-spellbookWrote 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/commands/kid-sid/claude-spellbook/mem_save)<a href="https://agentmods.dev/commands/kid-sid/claude-spellbook/mem_save"><img src="https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/mem_save.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 | $0.00000 | $0.00410 |
| Opus 5 | $0.00000 | $0.00205 |
| Sonnet 5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
mem_save 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 5d 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.
What it actually says
Save a curated session-level summary to history. Use this at meaningful milestones — end of session, before a long break, after wrapping a chunk of work — not after every turn. The auto-hooks (UserPromptSubmit, Stop, PreCompact) already capture turns; this command is for the higher-signal arc that those per-turn saves can't see.
Execute these in order in one response:
-
Call
ToolSearchwithquery: "select:mcp__memory_map__save_history"to load the schema. -
Distill the session arc into 4–8 lines covering:
- What we worked on — the actual task(s), not a turn-by-turn log
- Key decisions — non-obvious choices and the reasoning behind them
- Artifacts — files touched, commits, issues opened/closed, PRs (with refs)
- Open threads — anything started but not finished, or follow-ups identified
- Skip: routine acks, exploration deadends, and anything trivially recoverable from
git log
-
Pick 2–5 lowercase tags from the session content (comma-separated, no spaces): topic tags like
auth,mcp,refactor,bug-fix,migration,docs. These drive futuresuggest_historyrecall — pick the words you'd grep for next month. -
Call
mcp__memory_map__save_historywith:project_path: the current working directorydialogue: the distilled summary from step 2 (target 600–1500 chars)session_id: ""tags: the comma-separated tag string from step 3
-
Reply with just the returned chunk ID on one line. No recap, no explanation.
This is curation, not capture. The point is to leave a high-signal breadcrumb a future session can retrieve — not to duplicate what the per-turn hooks already store.
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.
- 5d ago First seen · 25 lines · 0 tokens per session scan A 208c9c4613a1
mem_save is a command published in the GitHub repository kid-sid/claude-spellbook (187 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 tokens. 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 2026-08-30.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.