Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/putervision/state-memory-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/putervision/state-memory-mcp/world-model-mcp)<a href="https://agentmods.dev/rules/putervision/state-memory-mcp/world-model-mcp"><img src="https://agentmods.dev/badge/rules/putervision/state-memory-mcp/world-model-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/putervision/state-memory-mcp/world-model-mcp"><img src="https://agentmods.dev/badge/rules/putervision/state-memory-mcp/world-model-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00673 | $0.00673 |
| Opus 5.5 | $0.00269 | $0.00269 |
| Sonnet 5.5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
world-model-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spatial World Model (world-model-mcp)
This project uses world-model-mcp with project slug "state-memory-mcp" to maintain a persistent 3D/2D spatial internal world model, entity tracking, object permanence, and movement simulation.
1. Mandatory Workflow & Priority
- Orient & Explore: Call
get_spatial_map(format: 'summary')andget_expected_viewat the start of spatial or simulated tasks. - Entity Queries: Use
query_entities(FTS5 search, proximity radius, or entity_id lookup) before creating duplicate objects. - Perception Bridging:
- Ingest detected objects from vision models using
ingest_observation. - Reconcile expected vs observed visual state using
ingest_observation(reconcile: true).
- Ingest detected objects from vision models using
- Spatial Relations: Record topological containment, support, or proximity using
set_relation(e.g.on,inside,next_to,contains). - Action Simulation & Validation: Before executing movement, call
simulate_movementto verify path validity and avoid AABB obstacle collisions, orsimulate_movement(mode: 'navigate')for waypoint planning. - Goal Alignment: Link target entities and destination regions to active
state-memory-mcptasks usinglink_to_goal. - Action Outcomes: Record movement success and entity mutations using
record_outcome.
2. Tool Reference Summary (15 Core MCP Tools)
update_entity: Create or update an entity (position, orientation, bounding box, properties, confidence).query_entities: Search entities by keyword, type, region, spatial proximity, tags, status, or lookup specific entity location/history.set_relation: Record/update spatial relationships (on, inside, next_to, above, below, near, contains).get_spatial_map: Export structured spatial layout, topological graph, 3D asset, or high-level summary.simulate_movement: Predict entity trajectory, test for AABB obstacle collisions, or compute navigation waypoints.ingest_observation: Merge perception detections into world model; re-identify entities and reconcile frustum view.get_expected_view: Calculate what entities should be visible from an observer pose and FOV cone.link_to_goal: Associate entities/regions with state-memory task IDs, or extract goal-relevant context slices.record_outcome: Update world model after action execution completes.manage_spatial_spec: Spatial SDD physical contract baseline registration, verification, and listing.create_evidence_pack: Generate cryptographic SHA-256 evidence packages linking spatial state to tasks.use_spatial_blackboard: Multi-agent shared spatial blackboard for publishing intentions and claiming mutex locks.manage_snapshot: Unified spatial snapshot and time-travel management (save, restore, diff, list, undo, history).generate_game_inputs: Generate Playwright MCP automation inputs or project/unproject 3D coordinates and screen pixels.wait_for_spatial_state: Poll and wait until an entity reaches a specific spatial condition.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 34 lines · 673 tokens per session scan A 40004bb854ed
world-model-mcp is a cursor rule published in the GitHub repository putervision/state-memory-mcp (48 stars, last pushed 13d ago), licensed MIT. It adds 673 tokens to every session, about $0.0027 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.