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 instructions/10xhub/agentflow/copilot-instructionsgit clone --depth 1 https://github.com/10xHub/AgentflowWhat 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 | $0.01520 | $0.01520 |
| Opus 5 | $0.00760 | $0.00760 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
Agentflow copilot-instructions.md 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for 10xScale Agentflow
Use these repo-specific notes to be productive quickly when generating code, docs, or tests.
Big picture
- 10xScale Agentflow is a lightweight Python framework for building multi-agent workflows with LLM-agnostic orchestration.
- Core primitives live in
agentflow/graph/:StateGraph,Node,Edge,ToolNode,CompiledGraph. - State is a Pydantic model (
state/agent_state.py); messages arestate/message.py::Messagewith multimodal content blocks (state/message_block.py). - Flow: build a
StateGraph→ add nodes/edges (incl. conditional) →set_entry_point→compile()→ useCompiledGraph.invoke()orCompiledGraph.stream(). - START/END constants come from
utils/constants.py(START="__start__",END="__end__"). Always reference these.
Architecture essentials
- Graph API (see
graph/state_graph.py,graph/compiled_graph.py,graph/node.py):add_node(name, func|ToolNode),add_edge(from, to),add_conditional_edges(from, condition, path_map).compile(checkpointer, interrupt_before, interrupt_after)wires DI (InjectQ), checkpointer, callbacks, publisher; default checkpointer is in-memory.
- Node contracts (
graph/node.py):- Functions accept
(state: AgentState, config: dict, …deps)and return updated state,list[Message], orModelResponseConverter. - Streaming supported by
.stream(...)andEventModelchunks.
- Functions accept
- Tools via ToolNode (
graph/tool_node/base.py):- Register plain callables or integrate MCP, Composio, LangChain. Get tool specs via
await tool_node.all_tools(). - Tool functions may declare injectable params like
tool_call_idandstate(see examples). - Supports parallel tool execution.
- Register plain callables or integrate MCP, Composio, LangChain. Get tool specs via
- Persistence & events:
- Checkpointers:
InMemoryCheckpointer(default) andPgCheckpointer(Postgres+Redis, extras required). - Publishers emit execution events (
ConsolePublisherfor dev). Events arepublisher/events.py::EventModel.
- Checkpointers:
- State management:
AgentStatehascontext(list of messages withadd_messagesreducer),context_summary, andexecution_meta(internal execution state).- Subclass
AgentStateto add custom fields while maintaining framework compatibility. - Use
BaseContextManagerfor custom context trimming logic.
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 · 78 lines · 1,520 tokens per session scan A 4a5f3ae51914
Agentflow copilot-instructions.md is an instructions file published in the GitHub repository 10xHub/Agentflow (20 stars, last pushed 17d ago), licensed MIT. It adds 1,520 tokens to every session, about $0.0076 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 instructions, from other repositories
ai-agents-for-beginners AGENTS.md
Instructions for microsoft/ai-agents-for-beginners, covering agents.md, project overview, setup commands, prerequisites and initial setup.
agent-framework python.instructions.md
Instructions for microsoft/agent-framework: See AGENTS.md for project structure and package documentation. Detailed conventions are in the agent skills under .github/skills/.
openacme CLAUDE.md
Instructions for sandydasari/openacme, covering openacme — claude code guide, workspace layout, the agent loop — request path, why sse-only and custom data parts.
agentfootprint AGENTS.md
Instructions for footprintjs/agentfootprint, covering agentfootprint — agent instructions (openai codex), core thesis, the mental model — three slots, six flavors, mock-first development (recommended workflow) and public api.
Framework_Development_Guide
Instructions for rezaho/MARSYS, covering 0. golden principle, 1. layered architecture (mental model), 2. core classes & responsibilities, 2.1 module overview & logical flow and src/agents/ - agent architecture & communication.
best-of-Agent-Harnesses CLAUDE.md
Claude Code instructions for RyanAlberts/best-of-Agent-Harnesses, covering repo notes for ai coding agents, commit identity (required), branching and pushing (required), verifying contribution credit (required) and how the list is generated.