Borrowing it
Nothing to install: this file belongs to zhinjs/zhin. 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/zhinjs/zhin/main/.github/instructions/zhin-plugin.instructions.mdgit clone --depth 1 https://github.com/zhinjs/zhinWrote 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/zhinjs/zhin/zhin-plugin)<a href="https://agentmods.dev/instructions/zhinjs/zhin/zhin-plugin"><img src="https://agentmods.dev/badge/instructions/zhinjs/zhin/zhin-plugin/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/zhinjs/zhin/zhin-plugin"><img src="https://agentmods.dev/badge/instructions/zhinjs/zhin/zhin-plugin.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 | $0.01745 | $0.01745 |
| Opus 5.5 | $0.00698 | $0.00698 |
| Sonnet 5.5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
zhin zhin-plugin.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 16d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zhin Plugin Runtime authoring
Package contract
- Every Plugin is an npm package with
package.json#zhin,plugin.tsand optionalschema.json. plugin.tsdefault-exportsdefinePlugin()fromzhin.js(Feature package authors may import from@zhin.js/plugin-runtimedirectly); it owns lifecycle and Resources, not capability registration.- Child packages live one level below
plugins/*. Logical ancestry comes fromzhin.plugins, not nested directories. - Feature providers are explicit
zhin.featuresmounts. Root apps that depend onzhin.jsinherit Stable Features viaplatformFeatures— they do not need separate@zhin.js/command/@zhin.js/middleware/@zhin.js/handler/@zhin.js/adapter/@zhin.js/componentunless a child peer requires a directly resolvable shared provider. This inheritance is root-only: child plugins must declare each Feature they use inzhin.features. Shared providers such as Command belong in optionalpeerDependencies, supplied by the host as a direct dependency so child resolution reaches the same physical package. Do not install a separate provider copy inside a mounted child; npm optional peers do not make the runtime Feature optional. See the first-plugin tutorial for both mount modes.
Convention directories
adapters/<name>/index.ts defineAdapter() // import from zhin.js/adapter
commands/**/index.ts defineCommand() // directory path is the route
components/<name>/index.ts defineComponent() // import from zhin.js/component
middlewares/<name>/index.ts defineMiddleware() // import from zhin.js/middleware
handlers/<name>/index.ts defineHandler() // explicit event supports dotted runtime names
tools/<name>/index.ts defineAgentTool()
hooks/<name>/index.ts defineHook() // import from zhin.js/agent
skills/<name>/SKILL.md Markdown Skill SSOT
skills/<name>/tools/<name>/index.ts Skill-private defineAgentTool()
agents/<name>/agent.json Agent metadata SSOT
agents/<name>/tools/<name>/index.ts Agent-private defineAgentTool()
agents/<name>/skills/<name>/SKILL.md Agent-private Skill SSOT
agents/<name>/skills/<name>/tools/<name>/index.ts
Agent-Skill-private defineAgentTool()
mcps/<name>/index.ts defineMcp()
schedules/<name>/index.ts defineSchedule()
pages/<name>/index.tsx definePage()
pages/{nav,footer}/index.tsx layout overrides
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.
- 16d ago Changed · +12 lines · +234 tokens per session f3e6c8192a9e
- 18d ago Changed · +10 lines · +278 tokens per session c54ab8421618
- 1mo ago Changed · +11 lines · +171 tokens per session eaa212b77380
- 1mo ago Changed · +3 lines · +44 tokens per session b8f2f48300f9
- 2mo ago First seen · 99 lines · 1,018 tokens per session scan A 465b09ed7ad0
zhin zhin-plugin.instructions.md is an instructions file published in the GitHub repository zhinjs/zhin (136 stars, last pushed today), licensed MIT. It adds 1,745 tokens to every session, about $0.0070 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.