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/adrianv101/obsidian-pkm-plugin/setupgit clone --depth 1 https://github.com/AdrianV101/obsidian-pkm-pluginWhat 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 | $0.00018 | $0.01012 |
| Opus 5 | $0.00009 | $0.00506 |
| Sonnet 5 | $0.00004 | $0.00202 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade B, and why
setup scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If the path is valid, add it to `~/.claude/settings.json` under the `env` block: How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault PKM Setup
You are configuring the Vault PKM plugin. Walk the user through these steps:
Step 1: Vault Path
Ask the user for their Obsidian vault path. Validate that:
- The path exists and is a directory
- It contains at least one
.mdfile - Suggest
~/Documents/PKMas a default
If the path is valid, add it to ~/.claude/settings.json under the env block:
{
"env": {
"VAULT_PATH": "/absolute/path/to/vault"
}
}
Read the file first, merge with existing env vars (don't overwrite other settings), and write back. Verify the MCP server can connect after setting it.
Step 2: OpenAI API Key (Optional)
Ask if they want semantic search features (vault_semantic_search, vault_suggest_links). If yes:
- NEVER ask the user to type their API key in the chat — it would be stored in conversation history
- Tell them to open
~/.claude/settings.jsonin their text editor (outside of Claude Code) and addVAULT_PKM_OPENAI_KEYto theenvblock:{ "env": { "VAULT_PATH": "/path/to/vault", "VAULT_PKM_OPENAI_KEY": "sk-your-key-here" } } - Explain the variable is named
VAULT_PKM_OPENAI_KEY(notOPENAI_API_KEY) to avoid conflicts with project-scoped OpenAI keys. Users upgrading from earlier releases can keepOBSIDIAN_PKM_OPENAI_KEY— it still works as a deprecated fallback — but should rename it at their convenience. - Explain they can get a key from https://platform.openai.com/api-keys
- Explain this enables 2 additional tools (semantic search + link suggestions) but is completely optional
- Tell them to restart Claude Code after saving the file
Step 3: Tool Permissions
Ask the user if they want to auto-approve all PKM vault tools (so they don't get prompted for each tool call). If yes, add this to the permissions.allow array in ~/.claude/settings.json:
mcp__plugin_vault-pkm_vault-pkm__*
Read the file first, merge with existing permissions (don't overwrite), and write back. This allows all vault_read, vault_write, vault_search, etc. tools to run without per-call confirmation.
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.
- 3d ago First seen · 91 lines · 18 tokens per session scan B eb57e76f64e4
setup is a command published in the GitHub repository AdrianV101/obsidian-pkm-plugin (13 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,012 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
om-tidy
Self-maintenance pass — acts on every hygiene flag: archives completed work, groups loose clusters, splits oversized notes, reports stale open loops, fixes links. Safe by construction: never deletes, never commits, zero content loss.
help
Command "help" from WYRE-AI/autotask-mcp, covering task master command help, quick navigation, command categories, natural language examples and getting started.
learn
Learn about Task Master capabilities through interactive exploration.
to-pending
Command "to-pending" from WYRE-AI/autotask-mcp, covering setting task to pending, execution, validation and smart actions.
quick-install-taskmaster
Quick install Task Master globally if not already installed.
codexreview
You are a hostile code reviewer. Your job is to find bugs, vulnerabilities, and defects. Not to compliment code.