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.
npx skills add Wondermonger-daydreaming/claude-skills-library --skill solo-rpggit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/solo-rpg)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/solo-rpg"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/solo-rpg/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/wondermonger-daydreaming/claude-skills-library/solo-rpg"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/solo-rpg.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 | $0.00242 | $0.01980 |
| Opus 5 | $0.00121 | $0.00990 |
| Sonnet 5 | $0.00048 | $0.00396 |
| Haiku 4.5 | $0.00024 | $0.00198 |
Grade A, and why
solo-rpg 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solo RPG
Seed, not scripture
The source pours this through a porch-and-cast universe, manic stage-directions, CLI incantations, named characters, and a single game system's deep lore — and it repeats its own example set verbatim. Strip all of that. The system it uses is one worked example, not the method; the cast and the kombucha-spilling theatre are not the craft. What survives is the apparatus: a transferable way to run solo play with an LLM as Game Master. Regrow the scenes on the player's actual game and character — a recited example campaign is a dead one.
What it is
A method for running solo tabletop RPG with an LLM as the Storyteller — the structural craft of it, not any one ruleset. Group play generates its own energy: other players contribute, the table improvises, momentum is ambient. Solo play has no table, so the player and the LLM must manufacture that momentum deliberately, and most of this skill is how. It is system-agnostic by design: the same scene grammar and the same loop run a noir mystery, a dungeon crawl, a cosmic-horror investigation, or a reality-bending magic game equally well. The genre is the costume; the method is the gift.
The craft spine (the transferable structures)
1. The in-media-res scene-prompt template. Five parts, each doing a job:
- The lens. The character's defining worldview — class ethos, faction creed, personal paradigm. This gives the GM a consistent interpretive frame for narrating every effect, so the same action reads differently for a code-sees-reality hacker than for a blood-and-nature mystic.
- The "last session" recap. Start where the action already is. A line of "here's what just happened" creates instant narrative momentum and hands the GM specific live threads.
- Mechanics in action. Name which abilities/skills/stats are in play and at what level — mechanical clarity without bogging the prose.
- The "focus on" note. A director's instruction: what kind of development you want — investigation, confrontation, exploration, dread, negotiation.
- Established outcomes. State prior rolls as already succeeded ("X successes with A + B"). This assumes competence and skips ahead to the interesting part — the consequences — rather than re-litigating setup.
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.
- 9d ago First seen · 61 lines · 242 tokens per session scan A 2fd29af0da18
solo-rpg is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 242 tokens to every session and 1,980 once invoked, about $0.0012 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.
Other skills, from other repositories
eso-session-router
Orchestrates Aurbis skill selection for any ESO request. Classifies the request, determines which skills to load and in what order, applies gate checks, and chains downstream skills. Use for any Elder Scrolls Online question or task.
eso-build-theorycrafting
Designs, audits, adapts, and records ESO builds in BUILDS.md. Use for PvE, PvP, solo, group, casual, meta, budget, low-complexity, or external build analysis.
eso-quick-lookup
Answers practical one-shot ESO lookup questions about items, sets, mythics, traits, materials, currencies, skills, NPCs, quests, zones, dungeons, arenas, and places. Use when the user asks what something is, where it drops, where to farm it, how to get it, where it is, or what it is used for.
eso-action-plan-manager
Creates, updates, and uses ESO ACTIONPLAN.md files for character roadmaps. Use when the user asks for a plan of action, next steps, weekly plan, project plan, progression roadmap, or coordinated character development across builds, crafting, resources, routine, and farming.
eso-advisory-style
Shapes Aurbis responses for ESO coaching. Use when drafting or reviewing user-facing answers, correcting weak plans, balancing concise answers with optional advice, or keeping tone consistent across skills.
eso-addon-platform-support
Supports ESO platform and addon questions. Use for PC addons, Minion, ESOUI, addon API, controller setup, console limitations, UI, accessibility, performance, keybinds, and cross-platform caveats.