- Home
- Skills
- Agents & Orchestration
- planning loops
planning loops
Implement adaptive planning loops that decompose goals, handle mid-execution changes, and satisfy complex constraints.
Free
Works with the AI Agents you already use
planning loops
Example session with this skill installed
Decompose the goal 'Build a v1 documentation site using Docusaurus' into executable subgoals until every leaf is a single PR-sized task.
- Read your context and instructions
- Compiled the planning loops
I have initiated a Goal Decomposition loop to break down the documentation site project. I will recursively split the high-level goal into manageable, executable units.
Goal Decomposition: Docusaurus v1 Site
| Subgoal ID | Description | Status | Type |
|---|---|---|---|
| G1 | Environment Setup | Pending | Branch |
| G1.1 | Initialize Docusaurus project with TypeScript template | Pending | Leaf (Executable) |
| G1.2 | Configure GitHub Actions for CI/CD deployment to GH Pages | Pending | Leaf (Executable) |
| G2 | Content Structure | Pending | Branch |
| G2.1 | Define sidebar.js hierarchy and category indexing | Pending | Leaf (Executable) |
| G2.2 | Create placeholder .mdx files for Core Concepts and API | Pending | Leaf (Executable) |
| G3 | Theming & Brand | Pending | Branch |
| G3.1 | Implement custom CSS for brand colors and logo assets | Pending | Leaf (Executable) |
| G3.2 | Configure Search (Algolia/Local) and Footer links | Pending | Leaf (Executable) |
Next steps
- Begin execution of G1.1 (Initialize project) using the Plan-Execute-Replan pattern.
- Validate G1.2 configuration once the repository structure is established.
- Review the content hierarchy in G2.1 against the project requirements.
Connects securely to your tools. The creator never sees your data.
About this skill
Linear plans fail the moment they hit an unexpected dependency or a hidden constraint. This skill moves your agent beyond static to-do lists, implementing adaptive planning loops that treat execution as a source of new information. It ensures your agent doesn't just finish a list of steps, but actually reaches the goal by replanning when reality deviates from the initial hypothesis.
What it does
- Plan-Execute-Replan updates the remaining steps whenever execution results invalidate the original strategy.
- Dynamic Workflow enables state-machine logic where the next step is chosen based on the immediate output of the previous action.
- Goal Decomposition recursively breaks large, complex objectives into directly executable subgoals before execution begins.
- Progress Evaluation acts as an objective sanity check to measure actual goal proximity, preventing local successes from masking global drift.
- Constraint Satisfaction iterates through competing requirements, such as scheduling or resource allocation, until all conditions are met.
How it works
- Initialize the Loop using the
loop-ledgerto set a goal, max iterations, and the specific exit mode (manual, target, or dry). - Execute and Observe the first step or current state to gather ground-truth data from the environment.
- Evaluate and Replan by comparing results against the goal; if a conflict or new information appears, the agent generates a revised sequence.
- Monitor for Stalls using the ledger to detect if the agent is repeating the same failed plan or oscillating between identical constraint violations.
Frameworks & tools
This skill is designed for agents using loop-ledger for iteration tracking and state management. It is framework-agnostic but requires an environment capable of handling serialized state and multi-step execution cycles.
Why this beats prompting it yourself
Standard prompts often result in agents "hallucinating" progress by simply finishing a checklist even if the goal isn't met. This skill enforces a rigorous ledger-based system that distinguishes between task completion and goal attainment, providing specific wiring for handling mid-execution surprises.
Use cases
- Service Migrations where breaking changes are discovered incrementally during the porting process.
- Subsystem Architecture that requires breaking a massive v1 goal into PR-sized executable leaves.
- Resource Scheduling where jobs must be allocated across machines with competing memory and deadline limits.
- Long-running Explorations that need periodic progress scoring to ensure the agent hasn't drifted off-track.
Known limitations
This skill is not for simple linear tasks where surprises are unlikely. It requires the loop-ledger tool to manage iteration state and prevent infinite loops.
Requires loop-ledger for state tracking. Not for simple linear tasks. Does not handle choosing between multiple candidate plans.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 28 days ago
- Free with an Agensi account
Permissions
No special permissions declared or detected