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.
npx agentmods add skills/av/harbor/new-boost-modulenpx skills add av/harbor --skill new-boost-modulegit clone --depth 1 https://github.com/av/harborWhat 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 | $0.00116 | $0.01798 |
| Opus 5 | $0.00058 | $0.00899 |
| Sonnet 5 | $0.00023 | $0.00360 |
| Haiku 4.5 | $0.00012 | $0.00180 |
Grade A, and why
new-boost-module 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 3d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Harbor Boost Modules
Harbor Boost is an optimizing LLM proxy with an OpenAI-compatible API. Modules are Python files that hook into the completion pipeline — they can rewrite prompts, inject system messages, chain multiple LLM calls, stream artifacts, or replace the completion entirely.
A module is activated by prefixing a model name with the module's ID_PREFIX. For example,
a module with ID_PREFIX = "mymod" is invoked via model mymod-llama3.1.
Before You Write Code
- Read the Custom Modules guide:
docs/5.2.1.-Harbor-Boost-Custom-Modules.md - Scan existing modules in
services/boost/src/modules/to find similar functionality you can reuse or learn from. There are 17+ built-in modules covering reasoning chains, prompt rewriting, structured output, artifacts, and more. - Read the Built-in Modules reference:
docs/5.2.3-Harbor-Boost-Modules.md
Understanding the available primitives (chat, llm, config, selection, log) saves
you from reinventing patterns that already exist.
Module Structure
Every module is a single .py file with two required exports:
ID_PREFIX = 'my_module'
async def apply(chat: 'Chat', llm: 'LLM'):
# Module logic here
pass
Required Exports
| Export | Type | Purpose |
|---|---|---|
ID_PREFIX |
str |
Unique identifier. Becomes the model prefix (e.g., mymod-llama3.1). Use lowercase, short, memorable names. |
apply |
async def(chat, llm) |
Entry point called for every matching completion request. |
Recommended Exports
| Export | Type | Purpose |
|---|---|---|
DOCS |
str |
Markdown documentation shown in the Boost modules reference. Include a description, parameters, and usage examples. |
logger |
Logger | Created via log.setup_logger(ID_PREFIX) for consistent, filterable logging. |
Core Primitives
chat — The Conversation
Chat is a linked list of ChatNode objects. The tail is the most recent message.
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.
- 3d ago First seen · 204 lines · 116 tokens per session scan A bcef6929ce49
new-boost-module is a skill published in the GitHub repository av/harbor (3,202 stars, last pushed 4d ago), licensed Apache-2.0. It adds 116 tokens to every session and 1,798 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
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.
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.
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.
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.
service-manage
Manage services in Kurtosis enclaves. Add, inspect, stop, start, remove, update services. View logs, shell into containers, and execute commands. Use when you need to interact with running services.
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.