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 instructions/jmjava/obsidian-mcp/copilot-instructionsgit clone --depth 1 https://github.com/jmjava/obsidian-mcpWhat 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 | $0.00419 | $0.00419 |
| Opus 5 | $0.00210 | $0.00210 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
obsidian-mcp copilot-instructions.md 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot: Obsidian Developer Memory
Use the obsidian-dev-memory MCP tools to keep durable engineering memory in the local Obsidian vault. The same server is used by Cursor. Obsidian does not need to be running.
When to read memory
Call get_project_context before substantial work when prior project memory is likely to help: continuing a feature, debugging a known area, making an architecture change, or explaining why the code is the way it is.
Do not call it for trivial edits.
Call search_memory before guessing about prior decisions. Use read_note only when you already have a vault-relative Markdown path.
When to record sessions
Call capture_work_session after meaningful work:
- an implementation
- an investigation
- a debugging session
- a migration
- an architecture change
- a research task
Do not record:
- typo fixes
- formatting-only changes
- trivial comments
- one-line mechanical edits
Prefer updating today's session note over creating duplicate notes.
When to record decisions
Call record_decision for architectural or engineering decisions that future work should know about, such as:
- 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.
When to update project state
Call update_project_state when the overall project state materially changes. Keep Project State.md concise. It is not a session log.
Daily notes
Use append_daily_note for short useful items on today's vault daily note. Do not overwrite existing daily-note contents.
Never store secrets
Never persist passwords, API keys, access tokens, refresh tokens, JWT values, private keys, .env contents, database credentials, production secrets, or sensitive customer data.
If a work summary contains secret-looking material, summarize it generically rather than persisting the literal value.
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.
- yesterday First seen · 58 lines · 419 tokens per session scan A 7ba52635ee7f
obsidian-mcp copilot-instructions.md is an instructions file published in the GitHub repository jmjava/obsidian-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 419 tokens to every session, about $0.0021 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.