Development guidance for the FlowLLM codebase, a framework for building applications that use language models. It describes how commands and clients connect through services, applications, jobs, steps, and components.

Use it when implementing, debugging, testing, reviewing, or documenting FlowLLM features such as command-line calls, services, jobs, streaming, configuration, and component registration.

It helps developers make changes that fit FlowLLM’s existing configuration and execution model instead of adding code that bypasses the framework.

flowllm-dev — Skill for Claude Code and Codex by FlowLLM-AI/flowllm

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.

Any agent

npx skills add FlowLLM-AI/flowllm --skill flowllm_dev

Clone the repo

git clone --depth 1 https://github.com/FlowLLM-AI/flowllm

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/flowllm-ai/flowllm/flowllm_dev/github.svg)](https://agentmods.dev/skills/flowllm-ai/flowllm/flowllm_dev)

Your own site

<a href="https://agentmods.dev/skills/flowllm-ai/flowllm/flowllm_dev"><img src="https://agentmods.dev/badge/skills/flowllm-ai/flowllm/flowllm_dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/flowllm-ai/flowllm/flowllm_dev"><img src="https://agentmods.dev/badge/skills/flowllm-ai/flowllm/flowllm_dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,630 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00065	$0.01630
Opus 5.5	$0.00026	$0.00652
Sonnet 5.5	$0.00013	$0.00326
Haiku 4.5	$0.00006	$0.00163

Measured 1mo ago against content hash b60e254d29ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flowllm-dev 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.

skills/flowllm_dev/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FlowLLM Development

Use this skill when changing or reviewing the FlowLLM repository. Treat the project as a configuration-driven LLM application framework whose execution path is:

CLI / Client -> Service -> Application -> Job -> Step -> Component

Prefer small, framework-shaped changes over ad hoc shortcuts. Read the local files before editing; the repository may move faster than this skill.

Start Here

Read these files first for most development tasks:

docs/zh/framework.md for the architecture and extension model.
docs/zh/contributing.md for development, tests, and contribution conventions.
flowllm/config/default.yaml for built-in jobs, components, defaults, and env-var placeholders.
The target implementation and nearby tests before making edits.

Use rg / rg --files for discovery. Do not assume a backend is available just because it appears in config; confirm it is registered and imported.

Repository Map

flowllm/application.py: application lifecycle, workspace setup, component/job instantiation, dependency ordering, CLI dispatch.
flowllm/config/config_parser.py: config file loading, dot-notation overrides, env-var expansion, scalar conversion.
flowllm/config/default.yaml: default HTTP service, jobs, and model/embedding/agent components.
flowllm/components/base_component.py: BaseComponent, lifecycle hooks, bind() dependency declaration, workspace paths.
flowllm/components/component_registry.py: global registry R, keyed by (ComponentEnum, backend_name).
flowllm/components/runtime_context.py: per-request data, response, stream queue, and mapping behavior.
flowllm/components/job/: BaseJob, StreamJob, background jobs, cron jobs.
flowllm/components/service/: HTTP and MCP service exposure.
flowllm/components/client/: CLI-side clients.
flowllm/steps/base_step.py: BaseStep, Ref, prompt loading, mapping, dispatch steps, job calls.
flowllm/steps/common/: built-in example/status steps.
flowllm/schema/: pydantic models for config, requests, responses, and stream chunks.
flowllm/enumeration/: component and chunk enums.
tests/unit/ and tests/integration/: preferred examples for test style and coverage boundaries.

Read the full file on GitHub · 180 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.

1mo ago First seen · 180 lines · 65 tokens per session scan A b60e254d29ca

Subscribe to this mod's changes

flowllm-dev is a skill published in the GitHub repository FlowLLM-AI/flowllm (36 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,630 once invoked, about $0.0003 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 2026-08-30.

Backend and APIs Data and AI LLM agent http-server llm-workflow mcp-server

data-leakage-detection

Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.

Tencent/AI-Infra-Guard · 34 tokens

groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

synthetic-sciences/openscience · 77 tokens

vllm

Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.

Prism-Shadow/penguin-harness · 29 tokens

knowledge-model-and-provider-runtime

A codebase guide for choosing AI models and providers, sending requests, recovering from failures, and recording runtime information.

echoVic/blade-code · 152 tokens

nornweave-api

Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…

DataCovey/nornweave · 77 tokens

LLM

Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.

jjyaoao/HelloAgents · 59 tokens