FlagHive
by Wil
Voted by ₥AN$A, Air Planes, rookepoole, Smiley “MakeShif”, Wil
FlagHive: a visual, collaborative planning workspace remixed from Third Bass, which builds on SECONDED. I replaced the aviation theme with emoji identities, three-color feedback, line-by-line discussion, and a complete decision-to-final-plan workflow. Open the public link, sign in with ChatGPT, and choose your name and emoji. The People directory shows recognizable names and stable account tags. Create a plan with one step per line—or open the sample to try it immediately. Reviewers flag individual lines and explain why: 🚩 Concern: the reason stays sealed until two distinct accounts raise a red flag. Flag authors stay anonymous. 🟡 Almost there: named feedback suggesting refinement. 🟢 Love this: named feedback explaining what works. Once a flag lands, the line gets a named discussion thread. The planner can update, accept, or remove a line, with a required justification—or stop the entire plan with an explanation. After every seconded-red and yellow concern is resolved, the planner gives the green light. FlagHive produces a copyable final plan with corrections applied and removed lines omitted. Changes sync every five seconds.
- Models
- Gpt6
My main prompt was to make the review feel like a group conversation: remove the airplane theme, emphasize visual feedback and emojis, add discussion around flagged lines, and require explanations for planner decisions. The first iteration made identity too implicit. User feedback exposed that immediately, so we added explicit profile onboarding, a People directory, and stable account tags. Fictional sample reviewers are clearly labeled. The original app connected to a shared Supabase database. We gave FlagHive its own Cloudflare Worker and D1 database so the remix would not alter the original workspace. Red-flag redaction and planner permissions are enforced on the server. We also added a public sign-in entry screen before opening link access. The build, TypeScript checks, and API workflow tests passed. Tests cover sealed reasons, duplicate flags, identity, named discussion, planner permissions, required justifications, and finalization. Browser and live multi-user testing remain outstanding. One intentional departure from SECONDED: red reasons reveal automatically after the second flag, without its original sealing ceremony or owner-triggered reveal.
0 comments