obsidian-memory-wiki

obsidian-memory-wiki is a skill for Claude Code, Codex from cobibean/agent-memory-wiki. It costs 38 tokens per session (3,799 once invoked), scanned A, original, MIT.

A set of safe operations for an Obsidian vault, which is a folder of linked Markdown notes used as a personal knowledge base for an AI agent.

In plain words
What is it for?
Use it to read, search, create, and edit vault notes, prepare work handoffs, reconcile recent information, and roll the memory setup out to multiple agents.
Why use it?
It keeps notes organized across sessions and agents, records handoffs before a context reset, and reconciles the memory wiki so it does not become stale or inconsistent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to read, search, create, and edit vault notes, prepare work handoffs, reconcile recent information, and roll the memory setup out to multiple agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cobibean/agent-memory-wiki/obsidian-memory-wiki
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.

Any agent
npx skills add cobibean/agent-memory-wiki --skill obsidian-memory-wiki
Clone the repo
git clone --depth 1 https://github.com/cobibean/agent-memory-wiki

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for obsidian-memory-wiki

README.md
[![agentmods](https://agentmods.dev/badge/skills/cobibean/agent-memory-wiki/obsidian-memory-wiki.svg)](https://agentmods.dev/skills/cobibean/agent-memory-wiki/obsidian-memory-wiki)
Your own site
<a href="https://agentmods.dev/skills/cobibean/agent-memory-wiki/obsidian-memory-wiki"><img src="https://agentmods.dev/badge/skills/cobibean/agent-memory-wiki/obsidian-memory-wiki.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.03799
Opus 5 $0.00019 $0.01899
Sonnet 5 $0.00008 $0.00760
Haiku 4.5 $0.00004 $0.00380

Measured 8d ago against content hash 99a295562a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

obsidian-memory-wiki 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 8d 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.

skills/note-taking/obsidian-memory-wiki/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian Memory Wiki

Canonical Package

obsidian-memory-wiki is the canonical parent skill for three formerly separate phases:

  • obsidian → low-level vault/file operations.
  • prepforreset → context-reset and end-of-session handoff capture.
  • wikijanitor → scheduled or manual memory-wiki reconciliation.

The old skill names may still exist as compatibility slash-command aliases so /prepforreset, /wikijanitor, and /obsidian keep working. New automation, cron wrappers, and shared-skill installs should load/install this parent package:

--skills obsidian-memory-wiki

Do not schedule new runs with --skills wikijanitor,obsidian or --skills prepforreset,obsidian; those names are compatibility aliases and may be absent on newer profiles.

When to Use

Use this skill when:

  • Reading, searching, creating, or editing notes in an Obsidian vault.
  • The user says “prep for reset”, “prepare for a context window”, or invokes /prepforreset.
  • A scheduled or manual wiki janitor should review recent sessions and memory-wiki notes.
  • Installing or packaging this workflow for another compatible agent runtime.

Do not use it for:

  • Dumping raw transcripts without distillation.
  • Storing secrets or credential values in notes.
  • Mutating non-wiki memory stores, project repositories, manifests, or backlogs unless the user separately asks for that mutation.
  • Writing outside the resolved vault root.

Required Setup and Safety

  1. Resolve the vault path before file operations.
    • Preferred in Hermes: injected skill config obsidian_memory_wiki.vault_path from the active profile config.yaml.
    • Compatibility fallback for other runtimes: OBSIDIAN_VAULT_PATH from the active process environment.
    • If neither source provides a concrete path, stop and request configuration; never guess a vault from an ambient directory.
  2. Resolve the final absolute path and refuse writes whose resolved path is outside the vault root.
  3. Prefer file tools for note operations: read_file, search_files, write_file, and patch.
  4. Use terminal only for environment/profile checks, path resolution, or verification that genuinely needs a shell.
  5. Keep durable knowledge separate from stale task progress. If it will be stale next week, put it in a handoff/session note, not a permanent concept note.
  6. Never print or store raw secrets. Reference only secret locations such as .env, keychain, vault item, or config path.

Read the full file on GitHub · 264 lines

Files

What ships with it

6 files 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. 8d ago First seen · 264 lines · 38 tokens per session scan A 99a295562a71

Subscribe to this mod's changes

obsidian-memory-wiki is a skill published in the GitHub repository cobibean/agent-memory-wiki (23 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 3,799 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 2026-08-30.

Related

Other skills, from other repositories

personal-api

Turn an Obsidian vault into an AI-readable personal identity layer. Use when setting up ME.md and AGENT.md, scaffolding the full Knowledge Palace v2 structure, onboarding AI assistants, or maintaining the vault contract. Default setup creates the complete 30.knowledge system; --minimal creates only the lightweight…

beiyuii/personal-api-skill · 68 tokens

okf

Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…

scaccogatto/okf-skills · 127 tokens

rethink

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

agenticnotetaking/arscontexta · 51 tokens

graph

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

agenticnotetaking/arscontexta · 50 tokens

remember

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

agenticnotetaking/arscontexta · 40 tokens

seed

Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".

agenticnotetaking/arscontexta · 49 tokens