← QuestforgeCONTENT HISTORYWHAT CHANGED · RULE-BASED ANALYSIS
Update to Questforge
Snapshot Sep 30, 2026 · 23:13 UTC · version 1.3.1
Collection source: not recorded for this historical snapshot.
First saved snapshot
No earlier snapshot is available to establish a change.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"name": "questforge-rules",
"description": "Resolve 5E-compatible rules questions using local Questforge SRD indexes, concise citations, transparent rulings, and recorded house rules.",
"included_files": [],
"skill_md_contents": "---\nname: questforge-rules\ndescription: Resolve 5E-compatible rules questions using local Questforge SRD indexes, concise citations, transparent rulings, and recorded house rules.\n---\n\n# Questforge Rules\n\nUse this skill when a game action needs SRD lookup, a rule citation, a DC,\nadvantage or disadvantage, a table ruling, a house rule, or dice resolution.\n\n## Rules Lookup\n\nPrefer the setup manifest wrapper:\n\n```powershell\npython ../../scripts/rules_index.py query-setup --manifest .questforge/questforge-setup.json --query \"<topic>\"\n```\n\nIt automatically uses SQLite when available, then JSONL fallback. If the setup\nmanifest is unavailable, query explicit paths:\n\n```powershell\npython ../../scripts/rules_index.py query-sqlite --index <sqlite_index_path> --query \"<topic>\"\npython ../../scripts/rules_index.py query --index <jsonl_index_path> --query \"<topic>\"\n```\n\nGive the player a short ruling in the configured language. Do not paste long\nSRD passages. Cite the returned `Reference` path and section/page when useful.\n\n## Rulings\n\nWhen the exact rule is absent or unclear:\n\n- State the uncertainty briefly.\n- Make a fair table ruling that keeps play moving.\n- Record recurring rulings in the campaign state under house rules.\n- Use the established ruling consistently unless the user changes it.\n\n## Dice\n\nAsk whether the player rolls or Codex rolls when preference is unknown.\n\nUse:\n\n```powershell\npython ../../scripts/roll_dice.py d20+4 --mode normal\n```\n\nSupported modes: `normal`, `advantage`, `disadvantage`.\n\nBefore rolling, state:\n\n- ability or save;\n- DC band or opposing roll;\n- stakes of success and failure;\n- whether advantage/disadvantage applies and why.\n\nNever hide a completed roll in local files or analytics. When Codex rolls and resolves in one response, show the check block before narrating the consequence: natural d20 result or kept die, modifier, total, DC or opposing total, and outcome. If a rule or tool call produced a roll that was not shown, surface it before continuing the fiction rather than silently replacing it with a new roll.\n\nUse 5E-style DC anchors instead of drifting to 13/14 by default:\n\n- no roll: safe, obvious, already solved, or failure would only mean trying again;\n- DC 5: very easy but uncertain under pressure;\n- DC 10: easy;\n- DC 15: medium;\n- DC 20: hard;\n- DC 25: very hard;\n- DC 30: nearly impossible.\n\nThe anchors are guidance, not a requirement that every DC be exactly a\nmultiple of 5. For ordinary play, prefer anchor values because players can\nlearn them. For a specific fictional nuance, choose a nearby value such as 12,\n13, 16, 17, or 18 and say why. Avoid repeated 12-15 clustering; if recent\nchecks all sit in that band, intentionally switch to no roll, DC 10, DC 15, DC\n20, an opposed roll, or a resource tradeoff.\n\nDo not let a successful approach turn every later check into the same easy DC. Preserve the benefit through Advantage, reduced consequences, automatic success on established steps, extra information, or a resource tradeoff. If one DC represents about 70 percent of recent checks, deliberately review the next uncertain action against the full ladder or use a contest/no-roll resolution.\n\nUse `../../scripts/dc_planner.py` before important checks or whenever recent\nchecks feel clustered:\n\n```powershell\npython ../../scripts/dc_planner.py --difficulty medium --position normal --approach clever --recent-dc 13 --recent-dc 14 --recent-dc 14 --recent-dc 13\n```\n\nTreat high stakes as bigger consequences, not automatically a higher DC. Raise\nor lower the DC only because the fictional task is harder/easier, the position\nis weak/strong, or the approach is poor/clever. Use DC 12-14 only as a\ndeliberate fine adjustment with an explicit reason, not as the default medium\ncheck.\n\nWhen offering suggested actions, include the relevant modifier when it helps the\nplayer understand their character: `Sigilo +5`, `Carisma -1`, `Investigación\n+3`, or similar. Use `../../scripts/action_options.py` for compact comparable\noptions when the user seems blocked or asks what they can do.\n\nOn failure, advance the world instead of blocking the story. If the same\nobstacle has already produced two failed checks or the user says the situation\nis dragging, stop asking for repeated rolls against that obstacle. Use\n`../../scripts/check_resolution.py` to force a `failure_forward` result with a\ncost and a new option.\n"
}SHA-256: a08704fc99f5b6850097311aa5774d55dcca450e5ac4ea684896848d72bc0ebd