Borrowing it
Nothing to install: this file belongs to AHappyAtlas/ai-knowledge-center. 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/AHappyAtlas/ai-knowledge-center/master/AGENTS.mdgit clone --depth 1 https://github.com/AHappyAtlas/ai-knowledge-centerWrote 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/ahappyatlas/ai-knowledge-center/agents-md)<a href="https://agentmods.dev/instructions/ahappyatlas/ai-knowledge-center/agents-md"><img src="https://agentmods.dev/badge/instructions/ahappyatlas/ai-knowledge-center/agents-md.svg" alt="Measured on agentmods" 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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
ai-knowledge-center 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 6d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Knowledge Center Agent Guide
Start Rule
- When the user says
按 ai-knowledge/LOAD.md 执行, 任务：..., readai-knowledge/LOAD.mdfirst, thenai-knowledge/core/LOAD.md, thenai-knowledge/ai/LOAD.md. - Optimize knowledge-token cost only on sparse triggers: explicit token/context/routing tasks, first run with no local token-check state, or changes to
AGENTS.md,ai-workflow.yaml,ai-knowledge/LOAD.md,ai-knowledge/core/**,ai-knowledge/ai/LOAD.md, orai-knowledge/skills/SKILL_INDEX.md. - The Agent must run the declared workflow scripts itself. Do not ask the user to manually run npm, yarn, pnpm, or aikc commands.
- Treat
ai-workflow.yamlas the project manifest for knowledge entrypoints, gates, MCP, telemetry, and dashboard metadata. - Treat
ai-knowledge/core/**as AIKC-maintained core workflow. Project-specific reusable knowledge belongs inai-knowledge/skills/**or project-owned references.
Project Shape
- This is a TypeScript/Vite/Fastify npm package that publishes the global CLI
aikcfromdist/cli/aikc.js. - Source lives under
src/; generated output lives underdist/. - The production CLI serves API and UI from one Fastify process. Development uses
tsx src/server/index.tsplus Vite. - Do not edit generated
dist/output unless the task explicitly asks for release artifacts; prefer source changes and runnpm run build.
Risk Boundaries
- Never overwrite existing human docs, project config, or uncommitted work. This checkout may not have a
.gitdirectory, so inspect files directly before changing them. - Do not introduce network-facing host changes casually. Binding to
0.0.0.0, changing ports, or exposing filesystem paths requires explicit task need. - The filesystem MCP must remain repository-scoped by default.
- Telemetry changes must preserve the documented ability to disable export with
AIKC_TELEMETRY_EXPORTER=none. - Do not persist one-off chat transcripts into the knowledge base. Only reusable constraints, workflows, failure modes, and validation knowledge belong here.
- Do not store project-specific lessons in
ai-knowledge/core/**; core files are upgraded from AIKC templates.
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.
- 6d ago First seen · 38 lines · 686 tokens per session scan A 7f40c75ce7b0
ai-knowledge-center AGENTS.md is an instructions file published in the GitHub repository AHappyAtlas/ai-knowledge-center (0 stars, last pushed 1mo ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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 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).
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.