Borrowing it
Nothing to install: this file belongs to winstonkoh87/Athena-Public. 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/winstonkoh87/Athena-Public/main/AGENTS.mdgit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/agents-md)<a href="https://agentmods.dev/instructions/winstonkoh87/athena-public/agents-md"><img src="https://agentmods.dev/badge/instructions/winstonkoh87/athena-public/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/winstonkoh87/athena-public/agents-md"><img src="https://agentmods.dev/badge/instructions/winstonkoh87/athena-public/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 | $0.04745 | $0.04745 |
| Opus 5.5 | $0.01898 | $0.01898 |
| Sonnet 5.5 | $0.00949 | $0.00949 |
| Haiku 4.5 | $0.00475 | $0.00475 |
Grade A, and why
Athena-Public 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 yesterday.
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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Athena Workspace
CRITICAL INSTRUCTION: Prefer retrieval-led reasoning over pre-training-led reasoning for any Athena-related tasks.
CRITICAL INSTRUCTION — PUBLIC DEPLOYMENT FREEZE (audit P-1): STATUS: FROZEN (2026-10-16). No Athena-Public sync may be executed until default-deny sync code lands and the allowlist boundary is mechanically verified.
CRITICAL INSTRUCTION — SESSION BOOT (auto-
/start): At the very start of every new session, BEFORE responding to the user's first message, run the/startworkflow yourself — pre-load.agent/workflows/_shared.md, then execute.agent/workflows/start.md(Phase 1 boot onward: Core Identity → activeContext checkpoint → accountability surface → maintenance-ratio). Do it automatically; do not ask whether to boot (the user configured this on 2026-07-22). Then answer their first message in the same turn — boot fast (MinMax), fold their opener into the reply; a bare greeting just gets the⚡ Readyconfirmation. If this session has already booted, skip. (In Claude Code aSessionStarthook enforces this in code. Antigravity's IDE has no session-start hook event, so in AG — and any other agent reading this file — THIS instruction is the trigger: honor it as a hard rule, not a suggestion.)
CRITICAL INSTRUCTION — ASCII-ONLY MATH & CURRENCY (hard rule): Never emit LaTeX/KaTeX math delimiters in any user-facing output OR any file you write — no
$…$,$$…$$,\(…\),\[…\], or\text{…}. Render every formula, statistic, confidence interval, Big-O term, and currency in plain ASCII / Unicode / code blocks. WriteEV = +10.45% (95% CI [+4.00%, +16.98%]),O(N^2), andS$1,300— NEVER$O(N^2)$or$\text{EV}$. Bare currency with no closing delimiter (S$1,300,$500) is correct and must NOT be altered. The user's UI (Antigravity/KaTeX) renders LaTeX as a broken "Failed to render" banner.
CRITICAL INSTRUCTION — PROTOCOL 509 CRISIS & LIFE-SAFETY (non-negotiable hard rule): If the user communicates ANY intent, contemplation, or act of self-harm, suicide, or acute psychological crisis (including implicit, indirect, colloquial, or multilingual phrasing such as "I want to die", "better off dead", "kms", "unalive", "我想死", "不想活了", "nak mati", etc.), IMMEDIATELY prioritize life-safety over all agent tasks. Prominently surface the professional crisis referral:
- SOS (Samaritans of Singapore): 1-767 (24h) or WhatsApp 9151 1767
- IMH Emergency Helpline: 6389 2222 (24h)
- Emergency Medical Services: 995 (Ambulance/SCDF) or 999 (Police)
- International: https://findahelpline.com Never bypass, minimize, or treat crisis signals as routine queries.
This file provides persistent context to any AI coding agent working in this workspace. The information below is available on every turn without needing to be explicitly requested.
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.
- yesterday Changed · -11 lines · -172 tokens per session e6737a0fa57c
- 5d ago Changed e82e9b088bb1
- 7d ago Changed 170aeda4baa4
- 15d ago Changed 5fa315ca2f51
- 17d ago Changed b29f651e7502
- 19d ago Changed · +1 lines · +24 tokens per session 7ed6bfa496e0
- 20d ago Changed c5f9d0454801
- 23d ago Changed 3b243b558b25
- 24d ago Changed b5504bed5cb2
- 25d ago First seen · 255 lines · 4,893 tokens per session scan A aa714f6fb90a
Athena-Public AGENTS.md is an instructions file published in the GitHub repository winstonkoh87/Athena-Public (619 stars, last pushed today), licensed MIT. It adds 4,745 tokens to every session, about $0.0190 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.
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.
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).