Plan
v1.0.0Auto-learns when to plan vs execute directly. Adapts planning depth to task type. Improves strategy through outcome tracking.
⭐ 2· 1.4k·6 current·10 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (adaptive planning + outcome tracking) match the actual contents: SKILL.md, strategies.md, and outcomes.md provide planning heuristics and tracking templates. The skill declares no binaries, env vars, or installs — consistent with an instruction-only planning helper.
Instruction Scope
Instructions stay within planning/tracking scope and do not direct the agent to read system files, call external endpoints, or access credentials. They are somewhat open-ended about where/how outcomes and tracking data are recorded (templates are provided but no explicit storage path or external endpoint), which could lead different agents to choose local files, a workspace, or external services — the skill does not specify or require any particular destination.
Install Mechanism
No install spec or code files; this is instruction-only, which is the lowest-risk install surface. No downloads, archives, or third-party packages are referenced.
Credentials
The skill requests no environment variables, credentials, or config paths. There are no disproportionate or unexplained secret requests.
Persistence & Privilege
always:false and default autonomous invocation behavior are used. The SKILL.md includes a 'promotion rule' that asks the agent to consider auto-starting certain plan types after multiple successful runs; combined with autonomous invocation, this could lead the agent to begin executing tasks without human validation for promoted types. This is expected behavior for an adaptive planner but worth confirming with policy controls or explicit confirmation steps.
Assessment
This skill appears coherent and low-risk for its stated purpose. Before installing, confirm two things with the skill author or your admin: (1) where and how outcome/tracking data will be stored (local files, agent workspace, or an external service) and whether those records contain sensitive details you don't want kept; (2) what exactly the 'promotion' / auto-start behavior does and whether you want the agent to be allowed to auto-execute promoted plan types without human confirmation. If you want tighter control, require human validation for promotions or restrict the agent's ability to write persistent records or execute tasks autonomously.Like a lobster shell, security has layers — review code before you run it.
latestvk97a1p15mjybhm7td5k2b9b3nn810w0j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.