← Back to Skills Marketplace
situated planning mode
by
Phallusophy
· GitHub ↗
· v1.0.0
· MIT-0
102
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install situated-planning-mode
Description
Use this when a user proposes a project or task that needs planning. Guide them through staged questions with options and descriptions to clarify goals, cons...
Usage Guidance
This skill is internally coherent and contains no hidden installs or credential requests. Before installing, confirm what your platform's sessions_spawn and memory APIs are permitted to access (internet, external APIs, and stored memory) because the skill explicitly instructs the agent to spawn research subagents and consult memory when it lacks knowledge. If you do not want the agent to perform network research or access stored memories automatically, restrict the skill's permissions or disallow autonomous subagent invocation. Otherwise, the skill appears safe for its stated planning purpose.
Capability Analysis
Type: OpenClaw Skill
Name: situated-planning-mode
Version: 1.0.0
The 'situated-planning-mode' skill is a well-structured framework designed to guide users through project planning using dynamic questioning and staged execution. It utilizes standard OpenClaw capabilities such as 'sessions_spawn' for subagent research and memory tools for context retrieval, all of which are aligned with its stated purpose of transforming vague ideas into clear plans. No indicators of data exfiltration, malicious execution, or prompt injection were found across the SKILL.md or reference files.
Capability Tags
Capability Assessment
Purpose & Capability
The name/description (planning assistant) match the SKILL.md: it guides users through staged planning questions, generates options+descriptions, and produces a plan. It does not request unrelated binaries, environment variables, or config paths.
Instruction Scope
Instructions are focused on planning and dynamic question generation. The skill explicitly instructs the agent to autonomously launch subagent research (sessions_spawn) when knowledge is insufficient and to call memory_search/memory_get for prior context. This is coherent with the stated purpose, but it gives the agent discretion to spawn research subagents and consult memory — review what those platform primitives can access in your environment.
Install Mechanism
No install spec and no code files are present (instruction-only), so nothing is written to disk or downloaded during install.
Credentials
The skill requests no environment variables, credentials, or config paths. The use of memory_search/memory_get and sessions_spawn is declared in the instructions and is proportionate to a planning/ research workflow.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes. It does permit autonomous subagent invocation per its instructions, which is consistent with platform defaults and the skill's research behavior.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install situated-planning-mode - After installation, invoke the skill by name or use
/situated-planning-mode - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Situated Planning Mode — From "do this" to "here's what happens if you do this".
This skill captures the AI-version of philosopher Kevin Zollman's (2011) intuition about the distinction between commands and descriptions: if your agent only provides you with options (a form of command, expressed in imperative mood) without providing descriptions related to those options (expressed in declarative mood), then you — the decision-maker — often face the problem of informational underdetermination. Through introducing the philosophical concepts to the front of SKILL.md, this skill systematically addresses this kind of problems.
There are three key advantages of this skill:
1. Dynamically generates planning questions based on project context — not a fixed question list (that's why it is called "situated")
2. Provides both options and descriptions during planning — so you decide with full information
3. Autonomously launches subagent research to enrich information when descriptions are insufficient — never guesses
Metadata
Frequently Asked Questions
What is situated planning mode?
Use this when a user proposes a project or task that needs planning. Guide them through staged questions with options and descriptions to clarify goals, cons... It is an AI Agent Skill for Claude Code / OpenClaw, with 102 downloads so far.
How do I install situated planning mode?
Run "/install situated-planning-mode" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is situated planning mode free?
Yes, situated planning mode is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does situated planning mode support?
situated planning mode is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created situated planning mode?
It is built and maintained by Phallusophy (@phallusophy); the current version is v1.0.0.
More Skills