Borrowing it
Nothing to install: this file belongs to 777genius/universal-agent-plugins. 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/777genius/universal-agent-plugins/main/AGENTS.mdgit clone --depth 1 https://github.com/777genius/universal-agent-pluginsWrote 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/777genius/universal-agent-plugins/agents-md)<a href="https://agentmods.dev/instructions/777genius/universal-agent-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/777genius/universal-agent-plugins/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/777genius/universal-agent-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/777genius/universal-agent-plugins/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 | $0.00819 | $0.00819 |
| Opus 5.5 | $0.00328 | $0.00328 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
universal-agent-plugins 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 2d 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.
Agent instructions
VS Code is frozen (owner decision, 2026-10-16)
Do not change VS Code implementation, adapters, protocols, configuration, or dedicated fixtures/tests. Preserve existing behavior and source. New dependency-managed installation and release work targets Claude, Codex, OpenCode, Cursor and Gemini; VS Code remains excluded. Reopening VS Code work requires a new explicit owner instruction.
Standard-first authoring: preserve legacy capabilities
For this authoring program, read docs/AUTHORING_CAPABILITY_PRESERVATION.md and the owner clarification at the top of the implementation plan. Do not delete useful plugin.yaml implementation, dependencies, tests or design documentation because plugin.json is narrower or a standard-first command no longer calls it. Retiring command exposure is distinct from removing source. Preserve unresolved capabilities outside the standard dependency graph. Any deletion requires an inventory item and explicit owner acceptance. Do not add implicit YAML fallback or a second supported engine. All hosted Codex workers for this program use gpt-6.1-sol with reasoning effort low for ordinary tasks and service tier default; raise effort only when the task requires it. Astra and fast mode are not authorized.
Public wording and release boundaries
Read the early-public-checkpoint owner decision in the implementation plan. D5 qualifies executable release; it does not block truthful public wording. Preserve PR190 availability labels and historical links. Never use DOCS_PREPARATION_PREVIEW in production or equate installer release proof with standard authoring release qualification. Use gpt-6.1-sol / low / default for ordinary hosted Codex tasks; raise effort only when needed. No Astra or fast. This owner instruction of 2026-10-26 supersedes older Astra assignments in plans and handoffs.
Owner release authorization (2026-10-08)
An explicit owner request to make or publish a release authorizes choosing and publishing the next suitable unused version within the same product and channels. Respect explicit constraints and report the chosen version; do not ask again solely for version selection or skipping a cancelled, never-public candidate. Preparation, review, and draft-only requests do not authorize public publication. All CI, independent review, environment, artifact, draft/promotion, and immutable tag requirements remain mandatory.
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.
- 2d ago Changed · +3 lines · +55 tokens per session eae04513bb35
- 4d ago Changed · +22 lines · +340 tokens per session a753acd8c471
- 12d ago Changed · +8 lines · +80 tokens per session 424a2276dc2e
- 19d ago Changed · +10 lines · +105 tokens per session ae188aff5124
- 1mo ago First seen · 23 lines · 239 tokens per session scan A 7c4312588ca9
universal-agent-plugins AGENTS.md is an instructions file published in the GitHub repository 777genius/universal-agent-plugins (14 stars, last pushed today), licensed Apache-2.0. It adds 819 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 2026-09-08.
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.