Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OSnpx agentmods add skills/dds-solutions/ai-tadpole-os/world-model-synthesisWrote 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/skills/dds-solutions/ai-tadpole-os/world-model-synthesis)<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/world-model-synthesis"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/world-model-synthesis/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/skills/dds-solutions/ai-tadpole-os/world-model-synthesis"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/world-model-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01952 |
| Opus 5.5 | $0.00014 | $0.00781 |
| Sonnet 5.5 | $0.00007 | $0.00390 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade A, and why
world-model-synthesis 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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Agent Skills Registry / world-model-synthesis
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: Model divergence, non-deterministic state transitions, infinite search expansion.
- Observability: Traceability via
execution/parity_guard.py([SKILL])
World Model Synthesis & Graph Search Planning Protocol
Knowledge Heritage: Inspired by Schema Harness (ARC-AGI-3 ~99% Public benchmark).
Source of Truth:execution/graph_planner.py,execution/backtest_engine.py
Overview
When agents encounter complex multi-step environment state changes (e.g. database schema migrations, deployment rollouts, infrastructure topology transitions), agents MUST NOT guess step-by-step actions in natural language. Instead, agents synthesize a programmatic world model (.tmp/world_model.py) and execute a local deterministic graph search (BFS or A*) to compute an optimal, zero-token action sequence.
🎯 Progressive Disclosure & L3 Reference Index
Read REQUIRED core workflow below; consult deep L3 Reference Guides on demand:
| L3 Reference Guide / Tool | Purpose | Trigger / When to Load |
|---|---|---|
references/world_model_templates.md |
Production templates for zero-downtime DB migrations, canary rollouts, and trace schemas | When synthesizing multi-branch world models or backtesting historical telemetry |
scripts/world_model_search.py |
Deterministic world model interface validator and BFS/A* local solver with --test suite |
Automated validation of synthesized models or running local plan computations |
🧭 Decision Matrix: When to Synthesize a World Model
| Scenario | Recommend World Model? | Justification |
|---|---|---|
| Multi-step state transition ($\ge 3$ dependent steps) | YES | Graph search eliminates compounding reasoning errors and verifies path safety. |
| Database schema migration or data backfill | YES | Pre-computes validation checkpoints, dual-writing gates, and rollback states. |
| Multi-stage service deployment / canary rollout | YES | Enforces health-check gates and rollback transitions deterministically. |
Single-shot command execution (e.g. npm test, git status) |
NO | Overkill; run deterministic CLI commands directly. |
| Linear script without branching or state rollback | NO | Standard procedural execution in execution/ is preferred. |
| Unbounded / infinite continuous state space | NO | Graph search requires discrete or discretized state transitions. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago Changed · +99 lines 6ba4d6b136a2
- 1mo ago First seen · 57 lines · 35 tokens per session scan A 51987e3f2c8a
world-model-synthesis is a skill published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,952 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
react-query-setup
Set up @trpc/tanstack-react-query with createTRPCContext(), TRPCProvider, useTRPC() hook, queryOptions/mutationOptions factories, query invalidation via queryClient.invalidateQueries with queryFilter, and type inference with inferInput/inferOutput.
trpc-router
Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, resolving TinyBase import paths, configuring browser or database…
beui-pro
Choose, inspect, install, and compose licensed beUI Pro premium React blocks through authenticated MCP or the shadcn registry. Use when building or improving landing pages with beUI Pro, installing @beui-pro items, selecting premium heroes, features, pricing, social proof, CTAs, navigation, footers, or other page…