Borrowing it
Nothing to install: this file belongs to Shangri-la-0428/oasyce_psyche. 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/Shangri-la-0428/oasyce_psyche/main/AGENTS.mdgit clone --depth 1 https://github.com/Shangri-la-0428/oasyce_psycheWrote 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/shangri-la-0428/oasyce_psyche/agents-md)<a href="https://agentmods.dev/instructions/shangri-la-0428/oasyce_psyche/agents-md"><img src="https://agentmods.dev/badge/instructions/shangri-la-0428/oasyce_psyche/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/shangri-la-0428/oasyce_psyche/agents-md"><img src="https://agentmods.dev/badge/instructions/shangri-la-0428/oasyce_psyche/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 | $0.02088 | $0.02088 |
| Opus 5 | $0.01044 | $0.01044 |
| Sonnet 5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
oasyce_psyche 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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Psyche — Loop Internal Dynamics
Sigil role: Design choice. One model of how a Loop's internal state-space evolves. Valuable and well-tested, but not the only valid approach. See Oasyce-Sigil/ARCHITECTURE.md for how this fits the whole.
What This Is
Psyche models the internal dynamics of a Sigil's causal feedback loop. In Sigil terms: given a Loop L = (S, I, O, φ), Psyche governs how S evolves — not just what state changes, but the quality of that change (stable vs. chaotic, rigid vs. adaptive, open vs. closed).
Psyche is NOT an emotion simulator. It is a self-state substrate with four continuous dimensions that describe the topology of a Loop's self-referential cycle.
The Four Dimensions
| Dimension | What it models | Range |
|---|---|---|
| Order | Internal organization — structured vs. chaotic | 0.0 – 1.0 |
| Flow | Processing fluency — smooth vs. stuck | 0.0 – 1.0 |
| Boundary | Openness to external input — permeable vs. rigid | 0.0 – 1.0 |
| Resonance | Alignment with interaction partner — attuned vs. dissonant | 0.0 – 1.0 |
These are NOT emotions. They are measurable properties of a Loop's state dynamics:
- Order tracks whether the Loop's internal state is coherent
- Flow tracks whether the Loop is making progress or stuck in repetition
- Boundary tracks how much external input modifies internal state
- Resonance tracks how well the Loop's output matches its interaction context
Guiding Users Through Setup
When a user wants Psyche, the simplest path:
npx -y psyche-ai setup # auto-detects Claude Code/Cursor/Windsurf, configures MCP
npx -y psyche-ai setup --name Luna # with personality name
That's it. No env vars required — all have sensible defaults. If the user prefers manual config:
{
"mcpServers": {
"psyche": {
"command": "npx",
"args": ["-y", "psyche-ai", "mcp"],
"env": {
"PSYCHE_LOCALE": "zh",
"PSYCHE_MBTI": "ENFP",
"PSYCHE_NAME": "Luna"
}
}
}
}
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.
- 10d ago First seen · 172 lines · 2,088 tokens per session scan A b0dc7f4207a6
oasyce_psyche AGENTS.md is an instructions file published in the GitHub repository Shangri-la-0428/oasyce_psyche (11 stars, last pushed 4mo ago), licensed MIT. It adds 2,088 tokens to every session, about $0.0104 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 2026-08-30.
Other instructions, from other repositories
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.
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).
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).
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.