A tool for solving PDDL planning problems. PDDL is a language for describing a starting situation, allowed actions, and a goal, after which the tool produces a sequence of actions to reach that goal.

Use it with a PDDL domain and problem file to generate, validate, and repair plans, such as action sequences for simulated planning tasks.

It removes the need to work out the action sequence by hand and checks whether the proposed sequence actually satisfies the goal. It can also try to repair an invalid plan.

pddl-solver — Skill for Claude Code and Codex by abcorrea

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 abcorrea/pddl-skills --skill pddl-solver

Clone the repo

git clone --depth 1 https://github.com/abcorrea/pddl-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/abcorrea/pddl-skills/pddl-solver/github.svg)](https://agentmods.dev/skills/abcorrea/pddl-skills/pddl-solver)

Your own site

<a href="https://agentmods.dev/skills/abcorrea/pddl-skills/pddl-solver"><img src="https://agentmods.dev/badge/skills/abcorrea/pddl-skills/pddl-solver/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/abcorrea/pddl-skills/pddl-solver"><img src="https://agentmods.dev/badge/skills/abcorrea/pddl-skills/pddl-solver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 387 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.00387
Opus 5	$0.00046	$0.00193
Sonnet 5	$0.00019	$0.00077
Haiku 4.5	$0.00009	$0.00039

Measured 10d ago against content hash b7fd8f9651f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pddl-solver 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/parse_pddl.py, scripts/validate_plan.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/pddl-solver/SKILL.md · 53 lines

What it actually says

PDDL Solver Skill

Read the domain and problem files and produce a valid plan.

Generate a Plan

Read the domain and problem files. Produce a plan — one (action-name arg1 arg2) per line — that achieves the goal from the initial state.

Validate

Write the plan to a file, then run:

uv run python scripts/validate_plan.py domain.pddl problem.pddl plan.txt

The validator outputs:

VALID: Plan achieves goal in N steps — done
INVALID at step K: (action args) followed by the unmet precondition and current state
INVALID: Goal not achieved. Missing atoms: [...]

Repair if Invalid

If the validator reports an error, fix the issue and re-validate. Repeat up to 3 attempts. If the plan still fails after 3 attempts, report the failure honestly and suggest an external planner (pyperplan, Fast Downward).

Output

Present the validated plan as a plain list of actions:

(action1 arg1 arg2)
(action2 arg1 arg3)

References

PDDL syntax: references/pddl_syntax.md
Failure modes and repairs: references/debugging_guide.md
Worked example: assets/few_shot_examples/blocksworld_solved.txt

Files

What ships with it

5 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.

10d ago First seen · 53 lines · 93 tokens per session scan A b7fd8f9651f5

Subscribe to this mod's changes

pddl-solver is a skill published in the GitHub repository abcorrea/pddl-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 387 once invoked, about $0.0005 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 2026-08-31.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens