oasyce_psyche: Instructions file for Codex

AGENTS.md

oasyce_psyche AGENTS.md is an instructions file for Codex, OpenCode from Shangri-la-0428/oasyce_psyche. It costs 2,088 tokens per session, scanned A, original, MIT.

Repository instructions for Psyche, a model of how a feedback loop's internal state changes in the Oasyce-Sigil project. It tracks organization, processing fluency, openness to outside input, and alignment with an interaction partner; these are system properties, not emotions.

In plain words
What is it for?
Setting up Psyche, understanding its four continuous dimensions, and connecting the project to MCP services while working within the repository's architecture.
Why use it?
They explain the project's specialized concepts and boundaries so an agent can configure and describe the system without treating it as an emotion simulator.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; built for openclaw.

This is Shangri-la-0428/oasyce_psyche's own configuration. It tells Codex and OpenCode how to work on oasyce_psyche itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oasyce_psyche configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is See [Oasyce-Sigil/ARCHITECTURE.md](../../Oasyce-Sigil/ARCHITECTURE.md) for how this fits the whole..

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Shangri-la-0428/oasyce_psyche/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Shangri-la-0428/oasyce_psyche

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for oasyce_psyche AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shangri-la-0428/oasyce_psyche/agents-md/github.svg)](https://agentmods.dev/instructions/shangri-la-0428/oasyce_psyche/agents-md)
Your own site
<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.

agentmods 80×15 button for oasyce_psyche AGENTS.md

Your own site · 80×15
<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>
Per session 2,088 This file is loaded in full into every session.
When invoked 2,088 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02088 $0.02088
Opus 5.5 $0.00835 $0.00835
Sonnet 5.5 $0.00418 $0.00418
Haiku 4.5 $0.00209 $0.00209

Measured 2mo ago against content hash b0dc7f4207a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

AGENTS.md · 172 lines

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"
      }
    }
  }
}

Read the full file on GitHub · 172 lines

Changes

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.

  1. 2mo ago First seen · 172 lines · 2,088 tokens per session scan A b0dc7f4207a6

Subscribe to this mod's changes

oasyce_psyche AGENTS.md is an instructions file published in the GitHub repository Shangri-la-0428/oasyce_psyche (11 stars, last pushed 6mo ago), licensed MIT. It adds 2,088 tokens to every session, about $0.0084 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.

Related

oasyce_psyche AGENTS.md compared with instructions from other repositories

oasyce_psyche AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
oasyce_psyche AGENTS.mdShangri-la-0428/oasyce_psycheInstructions file116mo agoMITA2,088Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode