Borrowing it
Nothing to install: this file belongs to meishanlaoyao/elysia-admin. 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/meishanlaoyao/elysia-admin/master/.kiro/steering/ai-ops-supplement.mdgit clone --depth 1 https://github.com/meishanlaoyao/elysia-adminWrote 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/meishanlaoyao/elysia-admin/ai-ops-supplement)<a href="https://agentmods.dev/instructions/meishanlaoyao/elysia-admin/ai-ops-supplement"><img src="https://agentmods.dev/badge/instructions/meishanlaoyao/elysia-admin/ai-ops-supplement/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/meishanlaoyao/elysia-admin/ai-ops-supplement"><img src="https://agentmods.dev/badge/instructions/meishanlaoyao/elysia-admin/ai-ops-supplement.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 | $0.00594 | $0.00594 |
| Opus 5.5 | $0.00238 | $0.00238 |
| Sonnet 5.5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
ai-ops-supplement 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 2mo 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.
What it actually says
AI Ops & Module Workflow (summary)
Full SOP:
#[[file:.ai/AI_MODULE_WORKFLOW.md]]
- Scaffold (CRUD boilerplate): #[[file:.ai/AI_MODULE_SCAFFOLD.md]]
Sub-guides:
- Page quality: #[[file:.ai/AI_PAGE_QUALITY.md]]
- Schema: #[[file:.ai/AI_SCHEMA_GUIDE.md]]
- Handoff SQL: #[[file:.ai/AI_HANDOFF_SQL.md]]
- MCP: #[[file:.ai/AI_MCP_SETUP.md]]
- Form layout: #[[file:.ai/AI_UI_LAYOUT.md]]
- Quick ref: #[[file:.ai/AI_CONTEXT_CAPSULE.md]]
Key points
- Flow: check
server/database/schema/→ scaffold (create:module+create:pagefromserver/) → dict (no hardcoded enums; short semanticdict_typee.g.goods_status; skip dict for pure boolean —.ai/AI_HANDOFF_SQL.md) → frontend polish → single SQL atserver/database/sql/{module}-init.sql - Rule-file language: when editing English AI rule docs, write new/changed prose in English (this edit only — no bulk translate)
- Postgres MCP: read-only for tables/dict/menu IDs; MUST prefer MCP over
pg.sql; never DDL/write via MCP - NEVER read or modify
server/database/sql/pg.sql— backup snapshot only; may not match live DB - Soft delete & uniqueness: uniqueness checks include soft-deleted rows; new unique → partial index
WHERE del_flag = false - Form validation both sides: frontend
rules+ backenddto.ts; entity dropdowns → cached/options(not/list) handle.tsJSDoc: every exported function needs purpose +@param/@returnsdb:push: after schema edits, check.ai/dev-preferences.local.md; ask once, then remember — see.ai/AI_SCHEMA_GUIDE.md- Handoff SQL: generate file only; developer runs manually; NEVER ad-hoc scripts/MCP execute
- Menu SQL: query live DB before INSERT; permissions match
route.tsand frontend auth - Page quality:
art-full-height,useDictStore, seeAI_PAGE_QUALITY.md - Git: AI read-only — no add/commit/push
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.
- 2mo ago First seen · 37 lines · 594 tokens per session scan A ff96ace3e13d
ai-ops-supplement is an instructions file published in the GitHub repository meishanlaoyao/elysia-admin (54 stars, last pushed 15d ago), licensed MIT. It adds 594 tokens to every session, about $0.0024 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 2026-09-06.
ai-ops-supplement compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-ops-supplementmeishanlaoyao/elysia-admin | Instructions file | 54 | 15d ago | MIT | A | 594 | Kiro |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | 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 |