boost-modules

A guide to writing custom Python modules for Harbor Boost, an LLM proxy that can intercept and transform chat-completion requests and responses.

In plain words
What is it for?
Use it to build reasoning workflows, prompt transformations, structured outputs, artifact handling, prompt-injection logic, or other middleware for chat completions.
Why use it?
It explains how modules connect to incoming conversations and the downstream language model, including ways to stream messages, show status, or run internal completions. This gives developers the structure needed to extend request handling.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/av/harbor/boost-modules
Any agent
npx skills add av/harbor --skill boost-modules
Clone the repo
git clone --depth 1 https://github.com/av/harbor

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01517
Opus 5 $0.00000 $0.00758
Sonnet 5 $0.00000 $0.00303
Haiku 4.5 $0.00000 $0.00152

Measured 2d ago against content hash 938edeb18490, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boost-modules scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

content += requests.get(url).text[:5000]
skills/boost-modules/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

---
name: boost-modules
description: Create custom modules for Harbor Boost, an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
---

# Harbor Boost Custom Modules

Boost modules are Python files that intercept chat completions and can transform, augment, or replace LLM responses.

## Module Structure

```python
ID_PREFIX = 'mymodule'  # Models prefixed with this trigger the module

async def apply(chat, llm):
    # chat: conversation history (linked list of ChatNodes)
    # llm: interface to downstream LLM and output streaming
    await llm.stream_final_completion()

Quick Reference

Output Methods

# Stream text to client
await llm.emit_message("Hello")

# Status indicator (formatted per HARBOR_BOOST_STATUS_STYLE)
await llm.emit_status("Processing...")

# Internal completion (not streamed to client)
result = await llm.chat_completion(prompt="Summarize: {text}", text=content, resolve=True)

# Streamed completion (visible to client)
await llm.stream_chat_completion(prompt="Explain {topic}", topic="quantum")

# Final completion (always streamed, even when intermediate output disabled)
await llm.stream_final_completion()
await llm.stream_final_completion(prompt="Reply to: {msg}", msg=chat.tail.content)

# Structured output
from pydantic import BaseModel, Field
class Response(BaseModel):
    answer: str = Field(description="The answer")
result = await llm.chat_completion(prompt="...", schema=Response, resolve=True)

# Artifacts (for clients like Open WebUI)
await llm.emit_artifact("<h1>Interactive content</h1>")

Chat Manipulation

# Read conversation
chat.text()           # Full conversation as string
chat.message          # Last user message content
chat.tail             # Last ChatNode
chat.tail.content     # Content of last message
chat.tail.role        # Role of last message
chat.history()        # List of messages from tail
chat.plain()          # List of ChatNodes from tail

Read the full file on GitHub · 208 lines

Changes

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.

  1. 2d ago First seen · 208 lines · 0 tokens per session scan A 938edeb18490

Subscribe to this mod's changes

boost-modules is a skill published in the GitHub repository av/harbor (3,198 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,517 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

docker-local-build

Build and test Kurtosis from source on local Docker. Compiles all components (engine, core, files-artifacts-expander), builds Docker images, installs the CLI, and restarts the engine. Use when developing Kurtosis and testing changes locally with Docker.

kurtosis-tech/kurtosis · 56 tokens

files-inspect

Inspect, download, upload, and debug Kurtosis file artifacts. View artifacts in an enclave, download them locally for inspection, upload local files, and troubleshoot file mounting issues. Use when services can't find expected files or configs are wrong.

kurtosis-tech/kurtosis · 51 tokens

k8s-dev-deploy

Build, push, and deploy Kurtosis dev images to a Kubernetes cluster without creating a release. Rebuilds engine, core, and files-artifacts-expander as multi-arch Docker images with a unique tag, pushes to the logged-in user's Docker Hub, and restarts the engine. Use when testing local code changes on a k8s cluster.

kurtosis-tech/kurtosis · 78 tokens

starlark-dev

Develop and debug Kurtosis Starlark packages. Create packages from scratch, understand the plan-based execution model, use print() debugging, handle future references, and test packages locally. Use when writing or troubleshooting .star files.

kurtosis-tech/kurtosis · 50 tokens

docker-debug

Debug Kurtosis running on local Docker. Inspect engine, API container, and service logs. Diagnose container crashes, port conflicts, and networking issues. Use when kurtosis commands fail or services aren't reachable on Docker.

kurtosis-tech/kurtosis · 45 tokens

enclave-inspect

Inspect and manage Kurtosis enclaves. List enclaves, view services and ports, examine file artifacts, dump enclave state for debugging, and clean up. Use when you need to understand what's running inside an enclave or export its state.

kurtosis-tech/kurtosis · 52 tokens