Borrowing it
Nothing to install: this file belongs to huisezhiyin/symphlo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/huisezhiyin/symphlo/main/AGENTS.mdgit clone --depth 1 https://github.com/huisezhiyin/symphloWrote 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.
[](https://agentmods.dev/instructions/huisezhiyin/symphlo/agents-md)<a href="https://agentmods.dev/instructions/huisezhiyin/symphlo/agents-md"><img src="https://agentmods.dev/badge/instructions/huisezhiyin/symphlo/agents-md/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.
<a href="https://agentmods.dev/instructions/huisezhiyin/symphlo/agents-md"><img src="https://agentmods.dev/badge/instructions/huisezhiyin/symphlo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01464 | $0.01464 |
| Opus 5 | $0.00732 | $0.00732 |
| Sonnet 5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
symphlo AGENTS.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 10d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
默认用中文交流；公共 API、协议字段、代码标识符和对外开发者文档使用英文。
Read First
进入 workspace 后按顺序阅读：
PROJECT_KNOWLEDGE.mdPROJECT_SPEC.mdREADME.mdPUBLIC_SOURCE_MANIFEST.md- 当前 task 对应的代码和测试
Owner Model
- 主 Agent 是 owner / decider / implementer / verifier。
- 中等及以上任务先明确 goal、scope、affected contracts、validation、risks 和 non-goals，获得 checkpoint 后再实现。
- 一次只推进一个最小可验收 task；每次收敛都回写受影响的 public contract、tests 和 release evidence。
- 保留用户已有改动；不重置、不清理、不顺手修无关文件。
Product Boundaries
- Symphlo is the durable Flow and collaboration control plane in the active
Symphlo + Clerkletproduct portfolio. The historicalhuisezhiyin/agent-flowproject is retired and must not receive new product work. - Symphlo coordinates multiple independent executors, not only fixed Agent chains. Agents, applications, MCP, HTTP, CLI, scripts, compute and Humans may collaborate through the same versioned Node and handoff contracts.
- Fixed and repeated orchestration is one strong Flow shape, not the complete product definition. Multi-Agent and multi-application collaboration is a core product scenario.
- Symphlo is not a general low-code platform and not an Agent UI shell.
- An Agent is a first-class Node executor. It may keep its internal loop, while Symphlo owns observable inputs, effects, executor identity, events, accepted results, Context and Artifacts.
- Symphlo guides Agent work through external task boundaries; it does not modify, expose or claim control over private Agent reasoning.
- Loop ownership slides with explicit Node granularity: broad Agent Nodes preserve more Agent autonomy, while finer semantic boundaries give the Flow more orchestration, evidence and recovery responsibility.
- Do not infer atomic work from a small task.
Agent Nodemay contain an opaque loop;model.task + model_cliguarantees one adapter request, whiletool.taskguarantees one fixed semantic CLI, MCP or HTTP operation and recordssymphlo.tool-call-evidence.v1. - Flow controls
what / who / when / dependencies / authority / handoff; each Agent or application controlshowinside its Node boundary. - Flow definitions, Run state, Context, Artifacts and history are product truth. Agent sessions and conversations are not.
- The public product must remain agent-agnostic and capability/adapter-driven.
- Clerklet is the separate standalone Agent and an optional reference participant. Neither repository may become the other's hidden runtime, database or source-path dependency.
- Canvas is optional infrastructure and must not define product identity or become the source of truth.
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.
- 10d ago First seen · 103 lines · 1,464 tokens per session scan A 5fabb3f2361a
symphlo AGENTS.md is an instructions file published in the GitHub repository huisezhiyin/symphlo (21 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,464 tokens to every session, about $0.0073 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
runtm copilot-instructions.md
Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).