How to Write Farcaster Channel Rules and a Welcome from a Mod Brief
Channel blurbs invent 12k followers and FID 12345. The brief allowed config snippets and banned affiliate links. Mods NONE. Channel UNKNOWN.
The matching generator is the Farcaster Channel Rules and Welcome from a Mod Brief (Not Captions) (Farcaster Channel Rules And Welcome From A Mod Brief Not Captions) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Write only the rule count the brief locked
Write Farcaster channel rules and a welcome from a mod brief. Not a caption engine. No invented member counts. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Mod brief I lock (topic, allowed casts, banned behaviors I name): [Brief]
Channel I may name (or UNKNOWN): [Channel]
Rule count I lock: [Count]
Words I must not use: [Banned]
What I must never invent (member counts, FIDs, extra bans): [Never]
Output format: [Format]
Language: [Lang]
Blurb character cap I lock: [SideCap]
Mods I may name (or NONE): [Mods]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Stay inside the blurb character cap
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Brief nouns, Channel, Count, SideCap, Mods, Lang. Forbidden: invented member counts, invented FIDs, extra bans.
- Rule list: Count rules from Brief only. Extra behaviors write NOT IN INPUTS.
- Blurb: stay at or under SideCap. Topic from Brief. Channel from Channel or CHANNEL UNKNOWN.
- Welcome: one short cast. Not a caption pack. No hashtag spray.
- Refuse list: Discord Automod YAML, Lemmy sidebar dump, Bluesky starter pack, Warpcast trending claims, caption engines.
- Mods: quote Mods or write NONE. Do not mint @admin.
- Never: do not write 12k followers. Do not invent FID 12345.
- Compliance pass: quote Banned and Never hits. Cut them. Print blurb character count. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Refuse Discord YAML and caption engines
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Farcaster channel rules and welcome from Brief only. Not Discord and not captions.
- Never invent member counts, FIDs, or extra bans.
- Honor Count and SideCap.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Print the blurb character count
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (farcaster channel rules, mod brief welcome, not a caption engine) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.