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/flowllm-ai/flowllm/flowllm_devnpx skills add FlowLLM-AI/flowllm --skill flowllm_devgit clone --depth 1 https://github.com/FlowLLM-AI/flowllmWhat 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 | $0.00065 | $0.01630 |
| Opus 5 | $0.00032 | $0.00815 |
| Sonnet 5 | $0.00013 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
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 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.
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 — 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.mdfor the architecture and extension model.docs/zh/contributing.mdfor development, tests, and contribution conventions.flowllm/config/default.yamlfor 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 registryR, keyed by(ComponentEnum, backend_name).flowllm/components/runtime_context.py: per-requestdata,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/andtests/integration/: preferred examples for test style and coverage boundaries.
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.
- 2d ago First seen · 180 lines · 65 tokens per session scan A b60e254d29ca
flowllm-dev is a skill published in the GitHub repository FlowLLM-AI/flowllm (34 stars, last pushed 2mo 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. 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
mem0-api
Complete reference for building applications with the Mem0 memory API and SDK — a persistent, self-improving memory layer for LLM agents and chatbots. ALWAYS use this skill when the user mentions: "mem0", "mem0ai", "MemoryClient", "Memory()", "memory layer for AI", "persistent agent memory", "long-term memory for…
metago-expert-world-model-architect
世界模型架构师。构建智能体的世界表征模型、世界预测引擎与行动规划系统。当涉及空间理解、环境感知、场景建模、具身智能推演时调用。.
metago-emotion
情绪检测技能。通过分析用户输入文本特征检测情绪状态。检测维度：词汇情绪词库、否定词与程度词处理、标点符号特征、长度与重复特征。返回emotionstate/confidence/intensity。.
metago-core
MetaGO Core Knowledge - 19 Meta-Thought Systems, 43 Fundamental Attributes, 36 Core Axioms, 13 Capability Families, 125 Engines, 984 Atoms, 927 Algorithms.
vector-search-patterns
Patterns for implementing in-process vector search in Akashic Context — cosine similarity in TypeScript, searchVectorInProcess(), hybrid merge integration. Preload into agents implementing Sprint 1.
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…