Borrowing it
Nothing to install: this file belongs to happy520ai/unified-ai-system. 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/happy520ai/unified-ai-system/master/AGENTS.mdgit clone --depth 1 https://github.com/happy520ai/unified-ai-systemWrote 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/happy520ai/unified-ai-system/agents-md)<a href="https://agentmods.dev/instructions/happy520ai/unified-ai-system/agents-md"><img src="https://agentmods.dev/badge/instructions/happy520ai/unified-ai-system/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/happy520ai/unified-ai-system/agents-md"><img src="https://agentmods.dev/badge/instructions/happy520ai/unified-ai-system/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 | $0.01642 | $0.01642 |
| Opus 5.5 | $0.00657 | $0.00657 |
| Sonnet 5.5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade C, and why
unified-ai-system AGENTS.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- BEGIN CODEX MANAGED: UNIFIED-AI-SYSTEM --> How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidance
Ownership
apps/agent-consoleowns operator interaction.apps/ai-gateway-serviceowns gateway runtime and Workbench behavior.packages/shared-contractsowns public protocol types.packages/shared-sdkowns reusable clients and adapters.packages/shared-configowns shared configuration.packages/shared-utilsowns implementation-neutral helpers.
Language and Module Policy
- For new changes,
apps/agent-consoleandapps/ai-gateway-serviceshould prefer TypeScript for runtime behavior and refactors. packages/*should remain TypeScript-first for contracts, SDKs, shared engines, and utility layers.- Tooling scripts under
tools/*.mjsshould remain Node.js ESM JavaScript. - Use JSON for schema and contract payloads, and Markdown for runbooks, evidence, and operator documentation.
- Introducing a new runtime language (for example Go or Rust) requires a measured rationale, migration boundary, and compatibility plan in the PR.
- For every PR that touches runtime code or scripts, follow
Language Selection Playbook:
define the workload, compare alternatives, document why the selected language is
the best fit, and capture rollback/compatibility impact.
PRs that do not include aLanguage Selectionsection using the playbook checklist are not considered merge-ready.
Public Repository Rules
- Keep application entrypoints under
apps/. - Keep reusable contracts, SDKs, configuration, and engines under
packages/. - Do not add generated phase ledgers, one-off verifier trees, or committed
runtime evidence to
master. - Generated evidence belongs under
apps/ai-gateway-service/evidence/and is ignored except for its README. - Historical engineering artifacts belong on the archive branch, not in the public product tree.
- Do not recreate
legacy/.
Safety
- Never read, print, or commit provider keys,
.env, raw webhooks, or private authorization records. - Real provider calls require explicit scoped authorization.
- Keep the local fake provider as the credential-free default.
- Do not silently modify
/chat, provider selection, deployment, or release behavior. - Do not claim production readiness, L5 autonomy, or AGI without independent evidence.
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 · +56 lines · +1,040 tokens per session scan A → C 5dbc8ea5fbf6
- 1mo ago First seen · 73 lines · 602 tokens per session scan A 11dff15c00a2
unified-ai-system AGENTS.md is an instructions file published in the GitHub repository happy520ai/unified-ai-system (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,642 tokens to every session, about $0.0066 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.