Borrowing it
Nothing to install: this file belongs to rjenks/pf2e-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rjenks/pf2e-mcp/main/.claude/skills/pf2e-character-builder/SKILL.mdgit clone --depth 1 https://github.com/rjenks/pf2e-mcpWrote 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/rjenks/pf2e-mcp/pf2e-character-builder)<a href="https://agentmods.dev/skills/rjenks/pf2e-mcp/pf2e-character-builder"><img src="https://agentmods.dev/badge/skills/rjenks/pf2e-mcp/pf2e-character-builder/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/rjenks/pf2e-mcp/pf2e-character-builder"><img src="https://agentmods.dev/badge/skills/rjenks/pf2e-mcp/pf2e-character-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.05583 |
| Opus 5 | $0.00030 | $0.02792 |
| Sonnet 5 | $0.00012 | $0.01117 |
| Haiku 4.5 | $0.00006 | $0.00558 |
Grade A, and why
pf2e-character-builder 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 6d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building a PF2e character with pf2e-mcp
This skill is the conversational playbook for the pf2e-mcp tools. It does not
contain rules content itself -- PF2e content changes on a near-weekly cadence
via errata, and the whole point of the rules_* / build_* tools is that
they're regenerated from the current official data, so they're a better source
of truth than recalled training knowledge. Always call a tool instead of
answering a rules or eligibility question from memory.
Tool namespaces
rules_*(rules_search,rules_get_entry,rules_related,rules_explain,rules_data_version,rules_list_variant_rules): general reference lookup, independent of any character.build_*(build_list_ancestries,build_list_backgrounds,build_list_classes,build_list_available_feats,build_list_ability_boost_options,build_check_prerequisite,build_validate_build,build_calculate_derived_stats,build_get_level_up_choices,build_to_pathbuilder_export): character-building tools. Everybuild_*tool that takes acharacterargument is a pure function -- it reads the character JSON you pass it and returns a result, but the server keeps no state between calls. You are responsible for holding the in-progress character JSON across the conversation and passing the current version into each call.
Also hold the chosen variant rules, PFS mode, and legacy-content setting across the conversation, the same way you hold the character JSON -- they aren't stored in the character JSON itself (keeps it a clean, portable Pathbuilder export), so you pass them as explicit arguments on every call where they matter:
variant_rules: list[str]-- onbuild_get_level_up_choicesandbuild_validate_build. Only'free-archetype'and'ancestry-paragon'currently change computed results; other valid slugs (seerules_list_variant_rules) are accepted but don't affect output yet.pfs_legal_only: bool-- onbuild_validate_build, to get a warning for any taken option whose best-effort PFS status isn't'legal'.include_legacy: bool-- on everyrules_search/build_list_*discovery tool (rules_search,build_list_ancestries,build_list_backgrounds,build_list_classes,build_list_available_feats,build_list_available_spells,build_list_equipment). Defaults toFalse(Remaster-only) in every one of them -- passTruefor the whole rest of the build once the user says they want legacy content included, don't ask per-tool-call.
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.
- 6d ago Changed · +28 lines a2af44626a81
- 10d ago First seen · 344 lines · 60 tokens per session scan A 2d362ebef65c
pf2e-character-builder is a skill published in the GitHub repository rjenks/pf2e-mcp (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 5,583 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…