persistence-state

A WorldForge helper for storing local run workspaces and artifacts under .worldforge/. Artifacts include run records, evidence bundles, evaluation and benchmark reports, and indexes; there is no persistent symbolic world database.

In plain words
What is it for?
Use it to manage run manifests, evidence and issue bundles, reports, retention and pruning, custom state directories, and JSON-compatible artifact validation.
Why use it?
It defines what local state may contain and validates saved data instead of silently accepting malformed or outdated files.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/abdelstark/worldforge/persistence-state
Any agent
npx skills add AbdelStark/worldforge --skill persistence-state
Clone the repo
git clone --depth 1 https://github.com/AbdelStark/worldforge

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00082 $0.00840
Opus 5 $0.00041 $0.00420
Sonnet 5 $0.00016 $0.00168
Haiku 4.5 $0.00008 $0.00084

Measured 3d ago against content hash 4f352e2d7d5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

persistence-state 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 3d 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.

.codex/skills/persistence-state/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persistence And State

Contract

  • WorldForge has no symbolic world store. The mutable World runtime, create_world/ save_world/load_world/export_world/import_world/fork_world, .worldforge/worlds, and the worldforge world CLI were removed in the latent-planning pivot. Planning is done with LatentMPCController over the score/predict capabilities; worldforge predict rolls a single move through a predict provider over an in-process world_state dict (not persisted).
  • The remaining local state is run workspaces and artifacts under .worldforge/ (default state_dir): run manifests, evidence/issue bundles, evaluation/benchmark reports, and run-index data. It is local-first and single-writer; hosts own durable storage.
  • All public/semi-public artifacts are JSON-native (string keys, finite numbers, lists, objects, bools, strings, null). Malformed persisted/provider artifacts raise WorldStateError; never silently coerce invalid state.
  • Treat existing .worldforge/ user state as off-limits unless the user points at a disposable directory. Tests must use tmp_path.

Workflow

  1. Build provider input world_state as a plain dict (e.g. {"schema_version":1,"id":..., "scene":{"objects":{obj.id: SceneObject(...).to_dict()}}}); pass it to forge.predict(...). There is no World object to mutate or persist.
  2. Use the run-workspace surface (worldforge runs ..., runs_prune, evidence bundles) for anything that must survive a process: write through the validated workspace/manifest APIs in src/worldforge/harness/workspace.py and src/worldforge/runs_prune.py.
  3. Validate serialized artifacts before filesystem writes and after reads; reject unsafe IDs, traversal, and non-JSON-native fields loudly.
  4. Keep CLI handlers thin; do not duplicate validation or file I/O rules in src/worldforge/cli.py.
  5. Test flows with tmp_path state dirs. Never use or delete the user's real .worldforge/ state.

Read the full file on GitHub · 58 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 58 lines · 82 tokens per session scan A 4f352e2d7d5b

Subscribe to this mod's changes

persistence-state is a skill published in the GitHub repository AbdelStark/worldforge (108 stars, last pushed 24d ago), licensed MIT. It adds 82 tokens to every session and 840 once invoked, about $0.0004 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

xie-saining-research-taste

Use when evaluating AI/ML research ideas, choosing research directions, framing problems, planning experiments, improving research taste or paper storytelling, resisting trend-following, or applying Saining Xie's interview-derived views on visual intelligence, world models, research culture, and scientific taste.

ky-ji/xie-saining-research-taste-skills · 63 tokens

improving-frontend-coverage

Runs frontend unit tests with coverage, analyzes coverage reports, and implements meaningful tests to increase coverage by 0.2%. Use when you want to systematically improve frontend test coverage with high-value test cases.

streamlit/streamlit · 48 tokens

hf-gradio

Use Gradio applications via API. Use when the user asks for to generate a prediction from a Gradio app on Hugging Face spaces or public URL. For example, "Generate an image using black-forest-labs/FLUX.2-dev".

gradio-app/gradio · 55 tokens

developing-with-streamlit

Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…

streamlit/streamlit · 128 tokens

hugging-face-paper-publisher

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

patchy631/ai-engineering-hub · 42 tokens

pr-review

Review a pull request and emit a validated review payload.

mlflow/mlflow · 14 tokens