agentleFS
Sign inStart free
tboome33tboome33/obsidian-mcp-router/skills/unlock/SKILL.md

unlock

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Lift the single-vault lock and restore normal multi-vault routing. Pass "persist" to ALSO lift the lock where a restart reads it from — the `locked` flag on this workspace's binding in the user's router config — and to remove the `OBSIDIAN_ROUTER_LOCKED` hint from the workspace `.env`. Without it, a lock recorded on the binding comes back at the next start; a leftover `.env` line on its own does not, since a lock named only by a project file is no longer applied.

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After a successful unlock, confirm to the user: previous lock target (if any), whether the .env was cleaned, and that the router is back in …

    line 26
  2. Distinctive:

    If the router wasn't locked, the tool returns a no-op message.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

unlock

Invoke the unlock_vaults MCP tool.

Argument parsing from $ARGUMENTS

  • empty → persist=false (in-memory only)
  • "persist" / "permanently" / "de manière permanente" / "et nettoie le .env" → persist=true
  • persist=true / persist=false — explicit

Always

  • After a successful unlock, confirm to the user: previous lock target (if any), whether the .env was cleaned, and that the router is back in normal multi-vault mode.
  • If the router wasn't locked, the tool returns a no-op message. Surface that gently — no need to be dramatic.
  • If the user said "persist" but the .env didn't have OBSIDIAN_ROUTER_LOCKED, the tool reports persistRemoved: false — surface that as an info ("nothing to clean up in .env"). The field that matters is bindingLifted: true means no lock is recorded for this workspace in the router config any more — either it was lifted, or there never was one — so nothing comes back at the next start. False means the router config could not be written, so a lock recorded there (if any) WILL come back; say that plainly and point at the config's permissions. Do not report a lock as "still recorded" on a false: the tool cannot see whether one existed when the write failed. One field overrides all of that: hostReimposes: true means the lock came from the host's OBSIDIAN_ROUTER_LOCKED (the MCP declaration or the shell), which no persist can lift — say plainly that it WILL come back at the next start until that variable is removed where it is set, and do not promise otherwise even though bindingLifted is true.

Push back if

  • The user wants to unlock and switch to a different vault in the same breath — that's two operations. Suggest /obsidian-router:lock <new-vault> directly (lock_vault overrides the previous lock without needing an unlock).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free