Skip to main content
Glama
billy12151
by billy12151

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PLAN_MODE_CLIENTNoClient identity for customization (e.g., openclaw, workbuddy, claude-code).
PLAN_MODE_DB_PATHNoPath to SQLite database file. Defaults to a local directory if not set.
PLAN_MODE_AGENT_IDNoAgent identifier for session isolation.
PLAN_MODE_ELICIT_TIMEOUTNoTimeout in seconds for elicitation request.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
enter_plan_modeA

Enter plan mode before attempting any complex, multi-step, or file-modifying task.

Use this PROACTIVELY for non-trivial coding, refactoring, or destructive operations. Once in plan mode you SHOULD:

  • research the task using read-only tools (read / grep / web search)

  • call todo_write to break the work into steps

  • then call exit_plan_mode with a concrete plan and WAIT for approval Avoid write / edit / exec while planning. This tool itself is non-destructive; it only marks state so the workflow is observable.

Args: reason: Short note on why plan mode is warranted for this task. goal: One-line description of what the plan should achieve.

exit_plan_modeA

Submit your completed plan and wait for user approval.

Call this ONLY after you have a concrete, actionable plan. This blocks the agent run until the user decides:

  • approve -> plan mode ends, write/edit/exec tools may be used

  • deny -> stay in plan mode, revise and resubmit On clients without in-tool approval prompts, the tool returns immediately with status 'submitted' and approval is deferred to the client's own permission flow.

Args: plan: The full step-by-step plan, in markdown. todos: Optional updated todo list to persist alongside the plan.

todo_writeA

Maintain the task list for this session.

Send the FULL list on every call — it replaces prior state (same semantics as Claude Code's TodoWrite). Each entry is {content, status, priority?} where status is one of pending / in_progress / completed and priority is high / medium / low. At most ONE entry may be in_progress at a time.

Args: todos: Complete replacement list. Empty list clears the todos.

get_plan_mode_standardsA

Fetch the full plan-mode rulebook.

Call this ONCE at the start of a plan-mode task (after enter_plan_mode, before writing your plan). It returns the standards that apply for the duration of this task: when to use plan mode, the workflow, coding discipline, tool discipline, and red lines for design/review tasks.

These standards are NOT auto-injected into every conversation — you fetch them on demand so they are in context when you actually need them. If unsure whether you have the latest version, re-fetch.

Returns: A dict with the standards text and a short note.

plan_recentA

List the most recent plans for debugging/observability.

Read-only — does not change any state. Useful for inspecting plan history (e.g. "what was the last rejected plan?") without opening the SQLite file directly.

Args: n: Maximum number of plans to return (default 10).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/billy12151/plan-mode-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server