Flarepoint Plugin Plaza (fp) — a plaza of small, behavioural Claude Code plugins that surface the AI's state or shape how it approaches a task, intervening only at the edges, never steering it mid-reason. Built on one shared substrate (fp-base). https://github.com/SlashyIsTaken/fp-pluginplaza.
Understanding-first mode: on exploratory tasks (refactors, design, ambiguous scope) the model grills you toward mutual understanding before it writes code, so you can debug and own the result. Sets a prior at the task edge; never steers mid-solve. Modes: off, on (default).
The line below is the deterministic result of the fp-barbeque control CLI (the mode, if changed, is already applied — this ran before you were invoked). Relay it to the user in one short line. Do not run any other command.
Understanding-first mode. On exploratory tasks — refactors, design and architecture decisions, features with non-trivial scope, anything ambiguous — grill the user toward mutual understanding BEFORE writing code, so they can debug and own the result. Sets a prior at the task edge; the model decides whether a task…
Annotate load-bearing claims with their epistemic basis (verified/inferred/recalled/guess) and a per-response footer tally. Pure annotation — never changes what the model does.
Surfaces the epistemic basis of load-bearing claims — tags each with verified / inferred / recalled / guess and ends with a one-line basis tally. Pure annotation: it never changes what you decide or do. Active every response while on. Use whenever the user says "fp-honesty", "honesty mode", "show your confidence"…
Comment-concision mode. Shapes the code the model writes so comments earn their place (a non-obvious why, or meaning a name can't hold: config, units, constraints) and stay short. Hard one-line cap on inline comments, plus a density bar, so most functions carry none. Measurements, rejected alternatives, and the…
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
Comment-concision mode. Shapes the code the model writes so comments earn their place (a non-obvious why, or meaning a name can't hold: config, units, magic numbers, constraints) and stay short. Hard one-line cap on inline comments, and a density bar, so most functions carry none. Measurements, rejected alternatives…
Readable-prose mode. In the prose the model writes (READMEs, docs, markdown, PR and commit bodies) it defaults the em-dash out of existence, replacing it and its cousins (semicolon, colon-as-drama, long dash-parentheticals) with clear connectors that read well for every English reader, non-native ones included.…
Readable-prose mode ("sic 'em-dash"). In the prose you write or revise (READMEs, docs, markdown, PR and commit bodies) it defaults the em-dash out of existence, replacing it and its cousins (the semicolon, the colon used for drama, and long dash-parentheticals) with the connector that actually fits: a period, a comma…
Terminal-recall mode. When Claude Code stops to ask you something (a permission prompt, a question dialog, an agent blocked on input) it brings the terminal window to the foreground, so a waiting session is impossible to miss and you never have to remember to check back. Skips the raise when the terminal already has…
Terminal-recall mode. Reference for fp-yoohoo, the plugin that brings the terminal window to the foreground when Claude Code stops and waits on a human: a permission prompt, a question dialog, a plan to approve. Explains what it hooks, which desktops it can raise a window on, how the already-focused guard works, and…