Fp Pluginplaza — AI skill for Claude Code
Flarepoint Plugin Plaza: small, single-purpose Claude Code plugins that fix one thing the model does that gets in your way, acting only at the edges of a task.
How to install Fp Pluginplaza
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Flarepoint-Systems/fp-pluginplaza and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Fp Pluginplaza does
Flarepoint Plugin Plaza: small, single-purpose Claude Code plugins that fix one thing the model does that gets in your way, acting only at the edges of a task.
Alternatives in AI
- Single File Agents — What if we could pack single purpose, powerful AI Agents into a single python file 433 ★
- Guild — Shared context, memory, and task coordination across AI coding agents 311 ★
- Real-World Pain Points — Project: https://github.com/Narwhal-Lab/MagicSkills For many teams building multi-agent systems, the first thi 277 ★
README
Flarepoint Plugin Plaza
Small, single-purpose Claude Code plugins. Each one fixes *one* thing the model does that gets in your way, cleanly, at the **edges** of a task, never mid-reason. Install only the ones you want.
| Plugin | What it does | Control |
|---|---|---|
| fp-barbeque | Grills you toward mutual understanding before it writes code on fuzzy-scope tasks | /fp-barbeque:mode |
| fp-honesty | Tags each claim with how grounded it is: 🟢 verified · 🟡 inferred · 🟠 recalled · 🔴 guess | /fp-honesty:mode |
| fp-sicem | Rewrites the em-dash (and its hard-to-read cousins) into punctuation anyone can read at speed | /fp-sicem:mode |
| fp-minify | Trims comments that just restate the code, keeps the ones that earn their place, capped at one line | /fp-minify:mode |
| fp-yoohoo | Brings the terminal to the front when Claude stops to ask you something | /fp-yoohoo:mode |
Install
/plugin marketplace add Flarepoint-Systems/fp-pluginplaza
/plugin install fp-sicem@flarepoint
The only requirement is `node` on your PATH. If `node` is missing, the plugins stay quiet instead of erroring.
See it
**fp-barbeque**: one focused question at the task edge, instead of building the wrong thing fast:
you › add caching to the API layer
without → starts wiring Redis across eight files.
with → "Before I build: in-memory per-process, or shared across
instances? And cache the HTTP responses or the DB queries?
Those have different blast radii. Which did you mean?"
**fp-honesty**: each claim carries its basis, with a tally to close:
Config loads from ~/.config 🟢, falls back to env vars 🟡, and the request
timeout defaults to 30s 🔴.
basis: 🟢 verified 1 · 🟡 inferred 1 · 🔴 guess 1
**fp-sicem**: the em-dash and its cousins rewritten into marks you
Related Skills
Claude Code Jev Router
Picks the model tier for a delegated Claude Code task before it spawns. Opt-in per repo, reversible in one com
Model Escalator
Claude Code mod that runs cheap models in parallel and escalates to a stronger one only when an agent gets stu
Oh My Fable
oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a mod
Aki
📍 Aki — show your AI agent exactly what to fix. Point at anything on your Mac and Claude Code, Codex or any a
Agent Dispatch
Free skill for Claude Code, Cursor and any agent client: picks the model for each subagent by the type of task
Going Dark
One strict way to run a software project with AI coding agents: issues as specs, handoff prompts, audits that
Related Agents
Implementer Simple
Implements one SMALL, bounded task test-first - a mechanical change, a rename, a config tweak, a fix touching
Task Runner
Owns the whole agent loop for ONE task. Main spawns it with a task and gets a single schema back; the runner r
Checkpoint Planner
Breaks a large feature into small, ordered, gated checkpoints and writes them as JSON to .ai-engineering/workf