agentleFS
JetXu-LLMJetXu-LLM/DocMason/skills/canonical/workspace-status/SKILL.md

workspace-status

Skill152 starsChanged 4 months agoApache-2.0View on GitHub

Inspect the current DocMason workspace stage and pending actions from the filesystem and runtime state.

4 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

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the task is to understand what stage the workspace is in and what should happen next.

    line 8
  2. Distinctive:

    If the agent cannot inspect the filesystem, stop and explain that the current workspace state cannot be determined safely.

    line 16
  3. Very specific:

    Use the reported stage, bootstrap_state, control_plane, and pending_actions as the authoritative workspace status summary.

    line 21
  4. Very specific:

    use the environment block to distinguish self-contained, mixed, and degraded

    line 22
  5. Very specific:

    treat only self-contained as ordinary ask-time ready

    line 23
  6. Very specific:

    Do not claim that a knowledge base exists unless status reports it as present.

    line 25
  7. Very specific:

    If the task is ambiguous, interpret pending_actions in context rather than as a rigid universal order.

    line 26
  8. Distinctive:

    When the workspace is stale or invalid, preserve that distinction instead of flattening it into a generic “not ready” message.

    line 34
  9. Very specific:

    When the stage is control-plane-pending-confirmation, preserve that state explicitly and surface the exact pending approval action such as …

    line 35

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Workspace Status

Use this skill when the task is to understand what stage the workspace is in and what should happen next.

Required Capabilities

  • local file access
  • shell or command execution
  • ability to reason about staged workflow state

If the agent cannot inspect the filesystem, stop and explain that the current workspace state cannot be determined safely.

Procedure

  1. Run docmason status --json.
  2. Use the reported stage, bootstrap_state, control_plane, and pending_actions as the authoritative workspace status summary.
    • use the environment block to distinguish self-contained, mixed, and degraded
    • treat only self-contained as ordinary ask-time ready
      • in practice this is the repo-local steady-state runtime the ask path may trust
  3. Do not claim that a knowledge base exists unless status reports it as present.
  4. If the task is ambiguous, interpret pending_actions in context rather than as a rigid universal order.
    • missing or stale adapter guidance matters only when the current flow depends on generated adapter files
    • missing or stale knowledge-base state matters directly for ordinary asking
  5. Return the final status interpretation to the main agent without mutating workspace state.

Escalation Rules

  • status is descriptive, not reparative. Do not silently switch into prepare, sync, or sync-adapters from inside this workflow.
  • When the workspace is stale or invalid, preserve that distinction instead of flattening it into a generic “not ready” message.
  • When the stage is control-plane-pending-confirmation, preserve that state explicitly and surface the exact pending approval action such as switch-host-to-full-access, prepare --yes, or sync --yes.

Completion Signal

  • The workflow is complete when the main agent has the authoritative workspace stage, environment readiness state, and next obvious actions.

Notes

  • status is derived from the filesystem and runtime state. There is no daemon or database.
  • bootstrap_state is the explicit cached-ready summary for ordinary ask-time reuse.
  • environment.toolchain_mode, environment.isolation_grade, and environment.entrypoint_health are the stable readiness fields for the prepared runtime.
  • control_plane is the authoritative summary for governed waits, approvals, and shared jobs.
  • Pending actions may include prepare, switch-host-to-full-access, sync-adapters, sync, and validate-kb.
  • Control-plane pending confirmations are authoritative status truth, not optional side notes.
  • A staged knowledge base with pending synthesis or blocking validation is reported as knowledge-base-invalid.
  • sync-adapters is an operator-maintenance action, not a universal prerequisite before every ask turn.

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.