pddl-skills

pddl-skills is a skill for Claude Code, Codex from benchflow-ai/skillsbench. It costs 44 tokens per session (718 once invoked), scanned A, original, Apache-2.0.

A toolkit for describing tasks in PDDL, a standard language for automated planning, then creating and checking step-by-step plans.

In plain words
What is it for?
Use it to load PDDL domain and problem files, generate classical plans, validate them, and save the results.
Why use it?
It removes the need to build planning logic from scratch and helps catch plans that do not reach their stated goals.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to load PDDL domain and problem files, generate classical plans, validate them, and save the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benchflow-ai/skillsbench/pddl-skills
About the project

SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.

benchflow-ai/skillsbench · 1,760 stars · on GitHub · skillsbench.ai

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.

Any agent
npx skills add benchflow-ai/skillsbench --skill pddl-skills
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/skillsbench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pddl-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/pddl-skills/github.svg)](https://agentmods.dev/skills/benchflow-ai/skillsbench/pddl-skills)
Your own site
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/pddl-skills"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/pddl-skills/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.

agentmods 80×15 button for pddl-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/pddl-skills"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/pddl-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 718 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00044 $0.00718
Opus 5 $0.00022 $0.00359
Sonnet 5 $0.00009 $0.00144
Haiku 4.5 $0.00004 $0.00072

Measured 7d ago against content hash adc4db64d255, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pddl-skills 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 7d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

tasks/pddl-airport-planning/environment/skills/pddl-skills/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements for Outputs

General Guidelines

PDDL Files

  • Domain files must follow PDDL standard syntax.
  • Problem files must reference the correct domain.
  • Plans must be sequential classical plans.

Planner Behavior

  • Planning must terminate within timeout.
  • If no plan exists, return an empty plan or explicit failure flag.
  • Validation must confirm goal satisfaction.

PDDL Skills

1. Load Domain and Problem

load-problem(domain_path, problem_path)

Description:
Loads a PDDL domain file and problem file into a unified planning problem object.

Parameters:

  • domain_path (str): Path to PDDL domain file.
  • problem_path (str): Path to PDDL problem file.

Returns:

  • problem_object: A unified_planning.model.Problem instance.

Example:

problem = load_problem("domain.pddl", "task01.pddl")

Notes:

  • Uses unified_planning.io.PDDLReader.
  • Raises an error if parsing fails.

2. Plan Generation

generate-plan(problem_object)

Description: Generates a plan for the given planning problem using a classical planner.

Parameters:

  • problem_object: A unified planning problem instance.

Returns:

  • plan_object: A sequential plan.

Example:

plan = generate_plan(problem)

Notes:

  • Uses unified_planning.shortcuts.OneshotPlanner.
  • Default planner: pyperplan.
  • If no plan exists, returns None.

3. Plan Saving

save-plan(plan_object, output_path)

Description: Writes a plan object to disk in standard PDDL plan format.

Parameters:

  • plan_object: A unified planning plan.

  • output_path (str): Output file path.

Example:

save_plan(plan, "solution.plan")

Notes:

  • Uses unified_planning.io.PDDLWriter.
  • Output is a text plan file.

4. Plan Validation

validate(problem_object, plan_object)

Description: Validates that a plan correctly solves the given PDDL problem.

Parameters:

  • problem_object: The planning problem.
  • plan_object: The generated plan.

Read the full file on GitHub · 142 lines

Files

What ships with it

4 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.

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. 7d ago First seen · 142 lines · 44 tokens per session scan A adc4db64d255

Subscribe to this mod's changes

pddl-skills is a skill published in the GitHub repository benchflow-ai/skillsbench (1,760 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 718 once invoked, about $0.0002 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 2026-09-03.