Borrowing it
Nothing to install: this file belongs to zhigege666/Lingshu-Gate. 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/zhigege666/Lingshu-Gate/main/AGENTS.mdgit clone --depth 1 https://github.com/zhigege666/Lingshu-GateWrote 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/zhigege666/lingshu-gate/agents-md)<a href="https://agentmods.dev/instructions/zhigege666/lingshu-gate/agents-md"><img src="https://agentmods.dev/badge/instructions/zhigege666/lingshu-gate/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/zhigege666/lingshu-gate/agents-md"><img src="https://agentmods.dev/badge/instructions/zhigege666/lingshu-gate/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 | $0.00830 | $0.00830 |
| Opus 5.5 | $0.00332 | $0.00332 |
| Sonnet 5.5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
Lingshu-Gate 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 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
These instructions apply to the entire repository.
Product identity and scope
- Use
Lingshu Gatefor the product,Gatefor short prose,lingshu_gatefor the Python package,lingshu-gatefor commands and artifacts,LINGSHU_GATE_for environment variables, andgate_for first-party MCP tools. - Use
MCPonly for the open protocol and its generic messages, transports, servers, tools, resources, and prompts. - Keep downstream connections vendor-neutral through the generic manifest and protocol transports. Use neutral examples and original project text.
- The only repository-owned Skill is
.agents/skills/lingshu-gate-upload-build-start/. It is part of the Project Delivery boundary and must retain confirmation, digest, idempotency, credential, and classification checks.
Architecture boundaries
- Keep protocol transport, application policy, persistence, and HTTP presentation separable.
- Control-plane writes require explicit permission checks and auditable events.
- Tool discovery never grants access. Classification review and publication remain distinct operations.
- Credentials are stored outside manifests, encrypted at rest, masked in responses, and never logged as values.
- Project upload, build, deployment, overwrite, startup, cancellation, and abandonment keep independent confirmation boundaries.
- Docker Core remains unprivileged, read-only at the root filesystem, and disconnected from container-engine sockets.
- SQLite deployment is single-writer and single-Core unless a different store is implemented and tested.
Change discipline
- Read the nearest code, tests, and documentation before editing.
- Preserve unrelated work in a dirty worktree.
- Prefer focused changes with tests for observable behavior.
- Failure paths must fail closed and return structured, actionable errors without secrets.
- Do not add silent fallback aliases for renamed package, environment, event, database, cookie, or tool identities.
- Use neutral commit and release text that describes the engineering result.
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 Changed · +9 lines · +224 tokens per session 4498f97ff0ad
- 2mo ago First seen · 57 lines · 606 tokens per session scan A a1559c73f980
Lingshu-Gate AGENTS.md is an instructions file published in the GitHub repository zhigege666/Lingshu-Gate (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 830 tokens to every session, about $0.0033 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 2026-08-31.
Lingshu-Gate AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Lingshu-Gate AGENTS.mdzhigege666/Lingshu-Gate | Instructions file | 0 | yesterday | Apache-2.0 | A | 830 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |