Agent skill

Persistence State

by AbdelStark in AbdelStark/worldforge

A skill your agent uses for WorldForge local state: run workspaces and artifacts under .worldforge/ (run manifests, evidence bundles, retention/prune), the WorldForge(statedir=...) directory, and…

MITAuto-check passedLegal & Compliance

Install Persistence State

skills CLI
$ npx skills add AbdelStark/worldforge --skill persistence-state -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AbdelStark/worldforge persistence-state --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AbdelStark/worldforge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/persistence-state .claude/skills/persistence-state && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
persistence-state
GitHub stars
108
Token cost
~921 tokens
SKILL.md length
389 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses for WorldForge local state: run workspaces and artifacts under .worldforge/ (run manifests, evidence bundles, retention/prune), the WorldForge(statedir=...) directory, and…

  • Works in 5 steps: Build provider input world_state as a… → Use the run-workspace surface… → Validate serialized artifacts before… → …
  • WorldForge local state: run workspaces and artifacts under .worldforge/ (run manifests
  • SKILL.md covers Contract, Workflow, Definition Of Done and Do Not Add, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Persistence State is an agent skill from AbdelStark/worldforge. Use for WorldForge local state: run workspaces and artifacts under .worldforge/ (run manifests, evidence bundles, retention/prune), the WorldForge(statedir=...) directory, and JSON-native artifact validation. The symbolic World JSON store and the worldforge world CLI were removed; there is no world persistence. Protects local state from silent corruption.

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Legal & Compliance, covering Dispute resolution. The repository describes itself as: Harness framework to build world model based workflows for physical AI systems. The licence is MIT.

When your agent uses it

  • WorldForge local state: run workspaces and artifacts under .worldforge/ (run manifests
  • Evidence bundles
  • Retention/prune)
  • The WorldForge(statedir=...) directory

Example prompts

  • “/persistence-state”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Build provider input world_state as a plain dict (e.g. `{"schema_version":1,"id":...,
  2. Use the run-workspace surface (worldforge runs ..., runs_prune, evidence bundles) for
  3. Validate serialized artifacts before filesystem writes and after reads; reject unsafe IDs,
  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.

What it can do on your machine

Read from SKILL.md and the folder at commit 30b65da. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Persistence State loads about 921 tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 389 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~921

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AbdelStark/worldforge at commit 30b65da, republished under its MIT licence (© AbdelStark). 389 words, ~921 tokens.

Download SKILL.mdSave it as .claude/skills/persistence-state/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
persistence-state
description
Use for WorldForge local state: run workspaces and artifacts under `.worldforge/` (run manifests, evidence bundles, retention/prune), the `WorldForge(state_dir=...)` directory, and JSON-native artifact validation. The symbolic `World` JSON store and the `worldforge world` CLI were removed; there is no world persistence. Protects local state from silent corruption.

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.
Show full SKILL.md (158 more words)Show less

Definition Of Done

  • Artifact validators reject unsafe IDs, malformed payloads, and non-JSON-native fields loudly.
  • CLI handlers delegate to the workspace/forge APIs rather than duplicating file I/O contracts.
  • Regression tests cover both the changed happy path and the invalid persisted/provider-state path.
  • Docs or command help include the command, success signal, and first recovery step when behavior changes.

Do Not Add

  • A symbolic world store, world persistence, or a worldforge world command (removed by design).
  • Lock files, SQLite/database adapters, remote persistence, or multi-writer service durability — these need explicit design approval because persistence is host-owned beyond local run state.

Sharp Edges

SymptomCauseFix
forge.predict ignores a moveworld_state dict has no scene.objects to moveSeed objects in the dict before predicting (mock mutates state["scene"]["objects"])
Run bundle/prune rejects an entryManifest or artifact payload invalidValidate the serialized payload against the workspace validators
Artifact leaks host paths/secretsUnsanitized field in a public artifactRedact via the provider/observable redaction helpers before writing

© AbdelStark, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .codex/skills/persistence-state of AbdelStark/worldforge.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 30b65da

Compare with similar skills

Persistence State next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Persistence State compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Persistence State this skillAbdelStark/worldforge108—~921Automated safety check: PassMIT
Litigation Deadline Calendarlawve-ai/awesome-legal-skills836—~4.3kAutomated safety check: PassMIT
Moot Court Simulation Buildercat-xierluo/legal-skills713—~1.4kAutomated safety check: PassCC-BY-NC-4.0
Intake To Draftstella/stella258—~537Automated safety check: PassApache-2.0
Nla Createinternet-court/internet-court-skill6.4k2 repos~915Automated safety check: PassMIT
Alkahest Userinternet-court/internet-court-skill6.4k2 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Litigation Deadline Calendar

    lawve-ai/awesome-legal-skills

    Calendar litigation and arbitration deadlines from a scheduling order.

    836 GitHub stars~4.3k tokensUpdated 6 days ago
    Legal & ComplianceAuto-check passed
  • Moot Court Simulation Builder

    cat-xierluo/legal-skills

    Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.

    713 GitHub stars~1.4k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Intake To Draft

    stella/stella

    Collects the facts of an unpaid invoice, then drafts a payment demand letter.

    258 GitHub stars~537 tokensUpdated today
    Legal & ComplianceAuto-check passed
  • Nla Create

    internet-court/internet-court-skill

    Create a Natural Language Agreement escrow on-chain. An agent skill from internet-court/internet-court-skill.

    6.4k GitHub starsUsed in 2 repos~915 tokens
    Legal & ComplianceAuto-check passed
  • Alkahest User

    internet-court/internet-court-skill

    Interact with Alkahest escrow contracts as a buyer, seller, or oracle using the CLI

    6.4k GitHub starsUsed in 2 repos~2.6k tokens
    Legal & ComplianceAuto-check passed
  • Nla Arbitrate

    internet-court/internet-court-skill

    Manually arbitrate NLA escrow fulfillments as an alternative to the automated oracle.

    6.4k GitHub starsUsed in 1 repo~866 tokens
    Legal & ComplianceAuto-check passed

More from AbdelStark/worldforge

  • Public Docs Release

    AbdelStark/worldforge

    A skill your agent uses for WorldForge README, docs, changelog, generated provider docs, MkDocs navigation, version/release metadata, public positioning, and release or publish readiness checks.

    108 GitHub stars~679 tokensUpdated 19 days ago
    Auto-check passed
  • Testing Validation

    AbdelStark/worldforge

    A skill your agent uses when selecting, running, or fixing WorldForge validation: pytest, coverage, ruff, generated provider docs, MkDocs strict build, package contract, CI failures, and release…

    108 GitHub stars~871 tokensUpdated 19 days ago
    Auto-check passed
  • Evaluation Benchmarking

    AbdelStark/worldforge

    A skill your agent uses for WorldForge evaluation suites, benchmark harness changes, benchmark input fixtures, budget gates, report rendering, metrics semantics, and any claims based on benchmark or…

    108 GitHub stars~732 tokensUpdated 19 days ago
    Auto-check passed
  • Optional Runtime Smokes

    AbdelStark/worldforge

    A skill your agent uses for LeWorldModel, GR00T, LeRobot, PushT robotics showcase, real-checkpoint smoke scripts, checkpoint building, and host-owned optional runtime dependencies.

    108 GitHub stars~855 tokensUpdated 19 days ago
    Auto-check passed
  • Provider Adapter Development

    AbdelStark/worldforge

    A skill your agent uses for WorldForge provider work: adding adapters, changing capability declarations, promoting scaffolds, debugging provider failures, updating provider catalog docs, or touching…

    108 GitHub stars~990 tokensUpdated 19 days ago
    Auto-check: notes
  • Tui Development

    AbdelStark/worldforge

    A skill your agent uses for the robotics showcase Textual UI: report panes, launch helpers, screenshots, visual tests, and changes under src/worldforge/harness/tui.py or robotics view/rendering…

    108 GitHub stars~792 tokensUpdated 19 days ago
    Auto-check passed

Questions about Persistence State

What does Persistence State do?

A skill your agent uses for WorldForge local state: run workspaces and artifacts under .worldforge/ (run manifests, evidence bundles, retention/prune), the WorldForge(statedir=...) directory, and…. Persistence State is an agent skill from AbdelStark/worldforge.) directory, and JSON-native artifact validation.

When should I use Persistence State?

Persistence State fits situations like: worldForge local state: run workspaces and artifacts under .worldforge/ (run manifests; evidence bundles; retention/prune); the WorldForge(statedir=...) directory.

How do I install Persistence State in Claude Code?

Run `npx skills add AbdelStark/worldforge --skill persistence-state -a claude-code`. Or copy the skill folder (.codex/skills/persistence-state in AbdelStark/worldforge) into .claude/skills/persistence-state in your project. Claude Code loads it when a task matches its description.

How do I install Persistence State in Codex?

Run `npx skills add AbdelStark/worldforge --skill persistence-state -a codex`. Or copy the skill folder (.codex/skills/persistence-state in AbdelStark/worldforge) into .agents/skills/persistence-state in your project. Codex loads it when a task matches its description.

Can I use Persistence State in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AbdelStark/worldforge --skill persistence-state -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/persistence-state, .gemini/skills/persistence-state, .github/skills/persistence-state and .opencode/skills/persistence-state in your project.

What does Persistence State need to run?

SKILL.md names no scripts, command-line tools or credentials: Persistence State is instructions for the agent only.

Does Persistence State access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Persistence State safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Persistence State use?

Persistence State is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Persistence State use?

About 921 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Persistence State?

Skills that share tags, products or a category with Persistence State: Litigation Deadline Calendar (lawve-ai/awesome-legal-skills, 836 stars), Moot Court Simulation Builder (cat-xierluo/legal-skills, 713 stars), Intake To Draft (stella/stella, 258 stars) and Nla Create (internet-court/internet-court-skill, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Persistence State?

AbdelStark (a GitHub user) maintains it in AbdelStark/worldforge, which has 108 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 19, 2026.

Source: AbdelStark/worldforge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.