owd-obsidian-mind

A legacy connection guide for linking an Obsidian Mind vault—a notes workspace with local search, linked information, and scoped memories—to MDevolved. It keeps the vault’s local tools, note layout, private-note rules, and multi-agent writing safeguards intact.

In plain words
What is it for?
Use it to connect or resume an Obsidian Mind vault, preserve its existing MCP connections, share approved Markdown information, and coordinate multiple writers through MDevolved.
Why use it?
It separates local memories and private notes from shared project information, reducing the risk of exposing runtime files or capturing unapproved content. It also provides a defined way to resume the correct project.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/msinclair25/mdevolved/owd-obsidian-mind
Any agent
npx skills add msinclair25/mdevolved --skill owd-obsidian-mind
Clone the repo
git clone --depth 1 https://github.com/msinclair25/mdevolved

Made for: Claude Code, Codex.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00100 $0.01220
Opus 5 $0.00050 $0.00610
Sonnet 5 $0.00020 $0.00244
Haiku 4.5 $0.00010 $0.00122

Measured yesterday against content hash 1612b85d80ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

owd-obsidian-mind 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.

packages/client-packs/owd-obsidian-mind/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDevolved + Obsidian Mind

Legacy compatibility path. New setups should use mdevolved-obsidian-mind; keep this pack for existing owd MCP entries and receipts.

Keep one universal MDevolved server. Apply this profile as client-side conventions; never change MCP framing, OAuth, or tool schemas for Obsidian Mind.

Confirm the runtime

  1. Read vault-manifest.json.
  2. Continue only when template equals obsidian-mind.
  3. Read AGENTS.md and CLAUDE.md.
  4. Preserve the existing .mcp.json entries. Add MDevolved beside qmd or om; never replace or proxy them.

Use these distinct roles:

  • MDevolved: remote OAuth boundary, exact Project UUID, owner approval, current Work Packet, provenance, Decisions, Artifacts, and handoffs.
  • Obsidian Mind om: local graph search, scoped recall, reasoning, and owner-authorized capture.
  • MDevolved Sync: Markdown transport. Do not use it to distribute Obsidian Mind scripts, hooks, settings, or other executable runtime files.

Connect or resume

Read .owdignore first. When present, call resume_project with its exact Project UUID and complete context policy. Never use .om-project, a folder name, or a display label as MDevolved authority.

In a fresh session, the writer role is unconfirmed until resume_project returns the current localVaultAccess.role. Never infer that a restarted session lost or retained primary status from chat history, session labels, or Mind tool availability. Treat MDevolved resume project and the legacy phrase OWD resume project as the same direct request to run this receipt-based resume; do not reconnect or request new authorization.

When no receipt exists, call open_project with the Project name the user gave. Do not ask the user to copy a prompt, reconnect, or choose New versus Existing before MDevolved reports that choice is genuinely required.

For a new Project:

  • use documentationPlan.decision = "keep-current-locations";
  • keep Obsidian Mind notes in their native folders rather than moving them to docs/;
  • choose the narrowest relevant concrete roots from work/active, work/archive, work/incidents, work/1-1, org/people, org/teams, perf/brag, perf/evidence, perf/competencies, brain, and reference;
  • never widen perf/h*-*/ to all of perf/; the automatic remote profile drops dynamic folder globs, so ask the owner to add an exact needed cycle such as perf/h2-2026 plus every other intended root to mcp_exposed_roots, which replaces the derived root list; and
  • use exact source note paths.

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 104 lines · 100 tokens per session scan A 1612b85d80ce

Subscribe to this mod's changes

owd-obsidian-mind is a skill published in the GitHub repository msinclair25/mdevolved (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,220 once invoked, about $0.0005 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 2026-09-01.

Related

Other skills, from other repositories

backups

Use when designing or auditing a backup-and-restore program that must survive a real disaster: setting defensible RPO/RTO targets, laying out 3-2-1-1-0 copies that are offsite and immutable, wiring point-in-time recovery, and proving restores work on a schedule. NOT tuning Postgres internals or writing the…

ericrisco/rsc-harness · 82 tokens

tfw-identity

Внутренний fail-closed механизм профилей и локальной привязки Assisted; отделяет участника, роли, task owner и роль ИИ.

saubakirov/trace-first-starter · 37 tokens

tfw-handoff

Command /tfw-handoff executes an approved Trace-First Workflow TS and creates ONB, implementation changes, evidence, and RF. Use for /tfw-handoff or implementation of an approved TFW task or phase.

saubakirov/trace-first-starter · 50 tokens

tfw-init

Command /tfw-init initializes Trace-First Workflow or attaches and repairs TFW tooling in an existing project. Use for /tfw-init, first-time setup, project discovery, adapter installation, or Codex adapter repair.

saubakirov/trace-first-starter · 49 tokens

tfw-knowledge

Command /tfw-knowledge consolidates Trace-First Workflow Fact Candidates into verified project knowledge. Use for /tfw-knowledge, the knowledge gate, fact promotion, topic files, or knowledgestate.yaml maintenance.

saubakirov/trace-first-starter · 48 tokens

tfw-review

Command /tfw-review reviews a completed Trace-First Workflow RF against its TS, implementation, and evidence. Use for /tfw-review, a TFW verdict, RF verification, or a REVIEW artifact.

saubakirov/trace-first-starter · 46 tokens