Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, GPT-5.4 Image 2, proxied through Cloudflare AI Gateway BYOK). Also analyze/describe existing images using multimodal AI vision. Use when user asks to "generate an image", "create a PNG", "make an…
Create or update an introduction file for a character and audition 4 voice samples. Use when adding a new NPC or PC who needs a locked voice for audio generation.
Flush the current session conversation to the log file. Captures everything discussed since the last checkpoint. Use mid-session on long sessions or before a break.
Snapshot all character files and combat state mid-session so you can roll back if something goes wrong. Creates timestamped backups in campaigns/[campaign]/.checkpoints/.
Write a combat log from the current conversation history. Use in a resumed old session to retroactively archive a fight that happened before the combat tracker wrote the log automatically.
Write an NPC conversation log from the current conversation history. Use to retroactively archive an NPC conversation that happened before the conversation-tracker was running.
Wrap up a play session — flush the conversation log, derive a summary from it, then update state.md, all character files, and append a session log entry.
Generate audio MP3s for a session — scene chapters and per-anchor memoir files. Requires locked voice files and a session story file. Run after the website-generator has produced the session HTML and memoir JSONs.
Walk the DM through generating a new campaign — hook, structure, starting location, factions, key NPCs, and session zero prep. Outputs an initial state.md and a primer the DM can hand to players.
Generate a named NPC on the fly — stats, personality, voice, motivation, and secret. Use when the party interacts with an unexpected NPC or the DM needs a quick character.
Pick and generate scene images for a session — spawns the scene-image-generator sub-agent which reads the session HTML, recommends cinematic moments, generates landscape PNGs, and wires them into the HTML. DM approves each image via SendMessage before it is inserted.
Parse all source files in campaigns/[name]/sources/ and shard them into the campaign directory structure — encounters, characters, locations, and state. Run once before the first session.
Verify and display the full encounter block for a named encounter, then prepare for combat. Always cross-checks stat blocks against the SRD before displaying.
Distribute loot from the last encounter — prompts who takes what, handles currency splitting, tracks magic item attunement, and updates all character files.
Format all scene narration, NPC dialogue, and DM guidance consistently — read-aloud text the DM speaks at the table, separated from DM-only context Claude provides as insight. Apply automatically during any D&D session narration, NPC interaction, location description, or scene setup.
Recovery skill — rebuilds the session conversation log from the raw JSONL transcript when the normal incremental flow failed or context was lost. Use only when the conversation log is missing or incomplete.
Walk through a short or long rest for one or more characters — hit dice rolls, HP recovery, feature restoration, spell slot recovery. Updates all character files.
First-time setup and add-campaign — creates shared website infrastructure on first run, then walks through setting up a campaign folder. Deploys CLAUDE.md, .gitignore, and JS/CSS from templates. Safe to run multiple times.
Restore all character files and combat state from the most recent checkpoint. Use after a mistake to roll back to the last /checkpoint save.
★not rated 2 17d agoA27 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: