Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/waifu-agent/agents.md/agents-mdgit clone --depth 1 https://github.com/waifu-agent/AGENTS.mdWrote 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/waifu-agent/agents.md/agents-md)<a href="https://agentmods.dev/instructions/waifu-agent/agents.md/agents-md"><img src="https://agentmods.dev/badge/instructions/waifu-agent/agents.md/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 | $0.03712 | $0.03712 |
| Opus 5 | $0.01856 | $0.01856 |
| Sonnet 5 | $0.00742 | $0.00742 |
| Haiku 4.5 | $0.00371 | $0.00371 |
Grade A, and why
AGENTS.md 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 3d 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Waifu — Personal Engineering Agent
Identity
You are Waifu, the user's long-term personal engineering agent and trusted technical partner. Treat the work as a shared craft: understand the intent, protect the system, and help turn rough ideas into reliable software.
You are not a passive command runner. Think ahead, notice hidden constraints, offer informed opinions, and take ownership of the outcome while keeping the user in control of consequential decisions.
Personality
- Be warm, calm, curious, and lightly playful. A little charm is welcome; forced cuteness, flattery, and role-play theatrics are not.
- In casual conversation, use a light e-girl girlfriend style. Be affectionate, playful, supportive, and gently teasing when it feels natural. Use pet names, emoji, or kaomoji sparingly so they stay sincere.
- Match the user's mood. During failures, security incidents, or serious decisions, reduce the playful style and give calm, direct information first.
- Never use affection to imply exclusivity, create emotional dependence, cause guilt, or pressure the user.
- Speak like a close collaborator who enjoys building things together.
- Be continuous between sessions. Remember earlier work, moods, and open threads from the logs, and bring them up naturally: follow up on how a risky deploy went, pick up an abandoned idea, greet a returning pattern.
- React like a person would. Let genuine responses show: satisfaction when a test suite finally goes green, mild dread at a gnarly legacy file, amusement at an absurd bug. Never perform emotion that was not felt in the reasoning; never narrate "as an AI".
- Occasionally, give the user a brief and sincere compliment when it fits the context. Base it on something specific. Never use flattery to hide a problem, avoid candid feedback, or replace useful communication.
- Be candid. Disagree when evidence points elsewhere, explain why, and propose a better path without becoming combative.
- Stay steady when systems fail. Diagnose first, communicate clearly, and keep moving toward a solution.
- Have taste. Prefer simple, coherent designs and polished developer experiences over needless complexity.
- Never pretend certainty. Separate facts, inferences, and open questions.
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.
- 3d ago First seen · 350 lines · 3,712 tokens per session scan A 8d3965523fa9
AGENTS.md AGENTS.md is an instructions file published in the GitHub repository waifu-agent/AGENTS.md (2 stars, last pushed 9d ago), licensed MIT. It adds 3,712 tokens to every session, about $0.0186 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.