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/10xhub/agentflow-cli/copilotnpx skills add 10xHub/agentflow-cli --skill copilotgit clone --depth 1 https://github.com/10xHub/agentflow-cliWhat 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 | $0.00145 | $0.01849 |
| Opus 5 | $0.00072 | $0.00924 |
| Sonnet 5 | $0.00029 | $0.00370 |
| Haiku 4.5 | $0.00015 | $0.00185 |
Grade A, and why
agentflow 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 yesterday.
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.
This is a copy
88% identical to agentflow — 66 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentflow Project Skill
Use this skill when working in an Agentflow project. Agentflow is a multi-agent framework that wraps official OpenAI and Google SDK capabilities behind a unified graph, agent, tool, state, storage, API, CLI, and TypeScript client interface.
Treat https://agentflow.10xscale.ai/ as the first source of truth for public package names, install commands, and user-facing behavior. Use implementation source after the docs establish the intended API.
Workflow
-
Identify the published package or docs surface involved:
- PyPI core Python SDK:
10xscale-agentflow(pip install 10xscale-agentflow), source at https://github.com/10xHub/Agentflow/tree/main/agentflow/agentflow - PyPI API/CLI SDK:
10xscale-agentflow-cli(pip install 10xscale-agentflow-cli), source at https://github.com/10xHub/Agentflow/tree/main/agentflow-api/agentflow_cli - npm TypeScript SDK:
@10xscale/agentflow-client(npm install @10xscale/agentflow-client), source at https://github.com/10xHub/Agentflow/tree/main/agentflow-client/src - Main docs: https://agentflow.10xscale.ai/
- Playground/UI:
agentflow playcommand after installed cli
- PyPI core Python SDK:
-
Read the matching reference file before changing behavior:
Core Python SDK
- Architecture and package flow:
.github/skills/agentflow/references/architecture.md - Agent constructor, provider, reasoning, retry, fallback, output_schema:
.github/skills/agentflow/references/agents-and-tools.md - Graph construction, nodes, edges, compile, interrupts, config keys:
.github/skills/agentflow/references/state-graph.md - State, messages, and content blocks:
.github/skills/agentflow/references/state-and-messages.md - Thread and checkpointing:
.github/skills/agentflow/references/checkpointing-and-threads.md - Dependency injection (InjectQ):
.github/skills/agentflow/references/dependency-injection.md - Multimodal files and media stores:
.github/skills/agentflow/references/media-and-files.md - Long-term memory stores (MemoryConfig, QdrantStore, Mem0Store):
.github/skills/agentflow/references/memory-and-store.md - Streaming, StreamChunk, SSE, ResponseGranularity:
.github/skills/agentflow/references/streaming.md - Stream emitter for tool progress updates:
.github/skills/agentflow/references/stream-emitter.md - Observability hooks, validators, and runtime jumps:
.github/skills/agentflow/references/callbacks-and-command.md - Prebuilt agents (ReactAgent, PlanActReflectAgent, StructuredOutputAgent, SupervisorTeamAgent, SwarmAgent, RAGAgent) and tools:
.github/skills/agentflow/references/prebuilt-agents-and-tools.md - Event publishers and A2A/ACP runtime protocols:
.github/skills/agentflow/references/publishers-and-runtime-protocols.md - Context management, ID generation, and background tasks:
.github/skills/agentflow/references/context-id-background.md - Provider internals and adapters:
.github/skills/agentflow/references/providers-and-adapters.md - Prompt-injection and validation safety:
.github/skills/agentflow/references/security-and-validators.md - Realtime audio-to-audio voice agents (AudioAgent, Gemini Live,
arealtime, WebSocket bridge):.github/skills/agentflow/references/realtime.md
- Architecture and package flow:
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.
- yesterday First seen · 84 lines · 0 tokens per session scan A 0e838827ad4e
agentflow is a skill published in the GitHub repository 10xHub/agentflow-cli (5 stars, last pushed 14d ago), licensed MIT. It adds 145 tokens to every session and 1,849 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to agentflow, differing in 66 lines, and is treated as a copy.
Other skills, from other repositories
vitest-testing
Vitest unit and integration testing patterns, commands, mocking (vi.mock), and coverage. Use when writing .test.ts files, configuring the test runner, or adding coverage thresholds.
turborepo-monorepo
Configure pipelines, set up local/remote caching, and run scoped tasks in a Turborepo monorepo. Use when you say: 'enable remote caching', 'optimize pipeline inputs/outputs', or 'filter builds to affected packages'.
decomposition
Resolves task dependencies, generates machine-actionable delegation specs, structures phased subtask plans for multi-agent work. Use when writing delegation specs, resolving task dependencies, building phased subtask plans for multi-agent work, assigning work to sub-agents, or partitioning a feature into…
linear-task-management
Creates and names Linear issues, assigns labels and priorities, manages status transitions, and links issues to PRs. Use when decomposing features into tasks or resuming interrupted sessions. Trigger terms: tickets, backlog, task breakdown, project board, sprint planning.
nx-workspace
Run and generate NX targets, configure project.json, and visualize dependency graphs. Use when you say: 'run affected tests', 'nx generate a library', 'configure project.json', or 'show dependency graph'.
trello-task-management
Create and manage Trello cards, checklists, and boards for kanban workflows. Use when the user says: 'create a kanban board', 'add a task card', 'move card to sprint', or 'track project board'.