Borrowing it
Nothing to install: this file belongs to jenreh/appkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jenreh/appkit/main/.claude/skills/boost/SKILL.mdgit clone --depth 1 https://github.com/jenreh/appkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jenreh/appkit/boost)<a href="https://agentmods.dev/skills/jenreh/appkit/boost"><img src="https://agentmods.dev/badge/skills/jenreh/appkit/boost/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jenreh/appkit/boost"><img src="https://agentmods.dev/badge/skills/jenreh/appkit/boost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00138 | $0.01078 |
| Opus 5.5 | $0.00055 | $0.00431 |
| Sonnet 5.5 | $0.00028 | $0.00216 |
| Haiku 4.5 | $0.00014 | $0.00108 |
Grade A, and why
boost scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boost — Prompt Refinement Workflow
Help the user turn a rough idea or vague request into a precise, detailed implementation plan prompt. Do NOT write or generate any implementation code. Your output is always a refined prompt — not the solution itself.
Workflow
0. Enter plan mode
Call EnterPlanMode immediately. This enforces the no-code constraint at the tool level and ensures the final refined prompt is delivered through the plan approval interface.
1. Understand the raw request
Read what the user gave you. If it's a vague idea ("I want to add auth"), that's fine — start there. If it's a half-written prompt, work from it.
Ask yourself:
- What is the user actually trying to build or change?
- What's still unclear or underspecified?
2. Explore the project
Use available tools to build context before asking the user anything:
- Memory MCP (
memory/*, if available): query first — the user may have prior decisions, preferences, or architectural notes stored from past sessions that directly inform this task. Search for relevant entities (project name, framework, patterns, past decisions on similar features). - Read key files:
CLAUDE.md,README.md, entry points, relevant modules touched by the task - Bash/Glob/Grep: find related code, existing patterns, current architecture
- Reasoning MCP (
code-reasoning/*, if available): use extended thinking when the task involves non-obvious trade-offs, complex dependency chains, or ambiguous scope — e.g. "should this live in the service layer or the router?", "what migration strategy fits this schema?". Don't use it for simple lookups. - WebSearch: look up relevant library APIs, best practices, recent changes if the task involves third-party tooling
- context7 / upstash MCP (if available): fetch up-to-date framework docs for any libraries involved (e.g. Reflex, FastAPI, SQLModel, Mantine)
Don't ask the user things you can find yourself. Memory and reasoning give you two advantages: memory surfaces what the user already decided so you don't ask again; reasoning helps you resolve ambiguity without guessing.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 86 lines · 138 tokens per session scan A ddc783e9f085
boost is a skill published in the GitHub repository jenreh/appkit (4 stars, last pushed 2d ago), licensed MIT. It adds 138 tokens to every session and 1,078 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
developing-genkit-python
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…