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.
git clone --depth 1 https://github.com/jmjava/obsidian-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/rules/jmjava/obsidian-mcp/obsidian-memory)<a href="https://agentmods.dev/rules/jmjava/obsidian-mcp/obsidian-memory"><img src="https://agentmods.dev/badge/rules/jmjava/obsidian-mcp/obsidian-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/rules/jmjava/obsidian-mcp/obsidian-memory"><img src="https://agentmods.dev/badge/rules/jmjava/obsidian-mcp/obsidian-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 | $0.00624 | $0.00624 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
obsidian-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 23d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Developer Memory
Use the obsidian-dev-memory MCP tools to keep durable engineering memory in the local Obsidian vault. Obsidian does not need to be running.
Before substantial work
Call get_project_context when existing project memory is likely to improve the work: continuing a feature, debugging a known area, making an architecture change, or answering "why is it like this?"
Do not call it for trivial edits.
After meaningful work
Call capture_work_session after a meaningful implementation, investigation, debugging session, migration, architecture change, or research task.
Do not create a memory entry for:
- typo fixes
- formatting-only changes
- trivial comments
- one-line mechanical edits
Prefer appending to today's session note over creating duplicate notes.
Durable decisions
Call record_decision when an architectural or engineering decision is made that future work should know about.
Examples:
- selected authentication architecture
- changed API boundaries
- selected persistence mechanism
- changed deployment strategy
- chose one library over another for a durable reason
If a decision file with the same generated name already exists, the server adds a numeric suffix instead of overwriting.
Project state
Call update_project_state when the overall project state materially changes. Keep that file concise. It is current state, not a session log. The tool merges a patch: omitted fields keep existing sections, and unknown H2s survive.
When claiming, blocking, unblocking, or finishing a Next Steps, Agent Queue, or TODO/*.md item, prefer list_open_tasks, list_blocked_tasks, claim_task, block_task, unblock_task, and complete_task over rewriting the whole state by hand. Those tools preserve other Project State sections, may check a matching Agent Queue checkbox or update a matching TODO note (claim_task / complete_task only), and do not overwrite daily notes.
Memory lookup
Call search_memory before guessing about prior decisions. It searches project memory plus top-level TODO/*.md and Daily/*.md. Use read_note only for a specific vault-relative Markdown path.
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.
- 23d ago Changed · +4 lines · +64 tokens per session 6489af1b63b2
- 1mo ago Changed · +2 lines · +137 tokens per session 1f453f0c27ce
- 2mo ago First seen · 71 lines · 423 tokens per session scan A 6a709cf3edfe
obsidian-memory is a cursor rule published in the GitHub repository jmjava/obsidian-mcp (1 stars, last pushed 23d ago), licensed MIT. It adds 624 tokens to every session, about $0.0025 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.