agent-reasoning-mcp / rules
Cursor rule22 starsChanged 47 days agoMITView on GitHub
This project uses agent-reasoning-mcp with project slug "agent-reasoning-mcp" to manage goals, decompose complex tasks, evaluate situational trade-offs, and track decision rationale.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,183 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/behavior-mcp.mdcCursor rule
- .cursor/rules/state-memory-mcp.mdcCursor rule
- .cursor/rules/vision-memory-mcp.mdcCursor rule
- .cursor/rules/world-model-mcp.mdcCursor rule
- docs/llms.txtllms.txt
- agent-reasoning-mcpSkill
- behavior-mcpSkill
- state-memory-mcpSkill
- video-ingestSkill
- vision-memory-mcpSkill
- webcrypt-mcpSkill
- world-model-mcpSkill
The file
We split this agent-reasoning-mcp.mdc into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Start of planning: Call set_goal(action: "create", title: "...") to establish high-level objectives.
- Very specific: line 8
Decomposition: Call set_goal(action: "decompose", parent_id: "...", subgoals: [...]) to break down into actionable steps.
- Very specific: line 9
Situational Trade-offs: Call evaluate_situation(action: "snapshot", snapshot: {...}) before selecting high-stakes actions.
- Very specific: line 11
Intention Dispatch: Create execution directives with manage_intentions(action: "create", ...) for the runtime engine.
- Very specific: line 12
Reactive Replanning: If an unexpected blocker occurs, invoke replan(action: "blocker", goal_id: "...", blocker_description: "...").
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- agent-reasoning-mcp:start -->
# Strategic Agent Reasoning (agent-reasoning-mcp)
This project uses `agent-reasoning-mcp` with project slug "agent-reasoning-mcp" to manage goals, decompose complex tasks, evaluate situational trade-offs, and track decision rationale.
## Mandatory Reasoning Workflow
1. **Start of planning**: Call `set_goal(action: "create", title: "...")` to establish high-level objectives.
2. **Decomposition**: Call `set_goal(action: "decompose", parent_id: "...", subgoals: [...])` to break down into actionable steps.
3. **Situational Trade-offs**: Call `evaluate_situation(action: "snapshot", snapshot: {...})` before selecting high-stakes actions.
4. **Utility Configuration**: Tune agent priorities with `set_utility_weights(action: "configure", weights: {...})`.
5. **Intention Dispatch**: Create execution directives with `manage_intentions(action: "create", ...)` for the runtime engine.
6. **Reactive Replanning**: If an unexpected blocker occurs, invoke `replan(action: "blocker", goal_id: "...", blocker_description: "...")`.
## 15 Core MCP Tools
- `set_goal`: Manage goal hierarchy and task DAGs.
- `evaluate_situation`: Score and rank candidate actions from environment snapshots.
- `replan`: Adaptively reconstruct subgoals upon obstacles.
- `assess_risk`: Quantitative threat and risk calculation.
- `query_knowledge`: Search heuristics and past decision patterns.
- `set_utility_weights`: Configure utility weights (aggression, caution, greed, exploration).
- `get_decision_trace`: Explainable chain-of-thought rationale playback.
- `manage_beliefs`: Structured belief state with exponential confidence decay.
- `manage_intentions`: Wire contract directives queue for runtime execution.
- `manage_reasoning_db`: Snapshots, diagnostics, and SHA-256 Merkle audit verification.
- `classify`: Zero-LLM deterministic classification against hierarchical taxonomy (<2ms SLA).
- `ask_noul`: Fast binary (Yes/No/Abstain) heuristic gate evaluating conditions (<2ms SLA).
- `ask_choice`: Deterministic multi-alternative selection ranking candidate choices (<2ms SLA).
- `ask_score`: Heuristic utility evaluation scoring target entities on a bounded scale (<2ms SLA).
- `gate_intention`: Fast-path safety & feasibility filter checking preconditions before execution (<1ms SLA).
<!-- agent-reasoning-mcp:end -->
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
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.