emotion-engine-codex

emotion-engine-codex is a skill for Codex from pioneerjeff-labs/emotion-engine. It costs 30 tokens per session (2,699 once invoked), scanned A, original, MIT.

A continuity layer for Codex workflows that stores a lightweight emotional state, an agent-to-user trust estimate, memories, and session patterns. It does not write replies itself.

In plain words
What is it for?
Use it in personal assistant projects, fictional-character tests, companion demos, or other workflows that need persistent interaction history.
Why use it?
It helps long-running or character-based workflows retain relevant context between sessions instead of treating every interaction as new.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .codex/skills/emotion-engine-codex/scripts/emotion_engine_mcp.py --state .emotion-engine/codex-state.json --locked-state --managed-runtime.

Good fit Use it in personal assistant projects, fictional-character tests, companion demos, or other workflows that need persistent interaction history.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pioneerjeff-labs/emotion-engine
agentmods
npx agentmods add skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex

Made for: Codex.

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 emotion-engine-codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex/github.svg)](https://agentmods.dev/skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex)
Your own site
<a href="https://agentmods.dev/skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex"><img src="https://agentmods.dev/badge/skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex/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 emotion-engine-codex

Your own site · 80×15
<a href="https://agentmods.dev/skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex"><img src="https://agentmods.dev/badge/skills/pioneerjeff-labs/emotion-engine/emotion-engine-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00030 $0.02699
Opus 5 $0.00015 $0.01350
Sonnet 5 $0.00006 $0.00540
Haiku 4.5 $0.00003 $0.00270

Measured 9d ago against content hash acc2749d8105, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

emotion-engine-codex 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (install.sh, scripts/codex_emotion.sh, scripts/nora_demo.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

integrations/codex/emotion-engine-codex/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Emotion Engine For Codex

Use this skill when the user wants Codex to maintain lightweight emotional continuity across local projects, fictional character tests, companion-style demos, or long-running personal assistant workflows.

Emotion Engine is not a chatbot and does not generate replies by itself. Codex still interprets the situation, decides the final emotional meaning, and writes the reply. Emotion Engine persists continuity: PAD state, agent-to-user trust, decay, compact emotional memories, and session patterns.

Trust is agent-to-user only: it is the agent/persona's internal continuity estimate of whether this user has been cooperative, boundary-respecting, predictable, and safe enough for deeper persona continuity. It does not infer the user's trust in Codex or in the agent.

Quick Reference

Use the project wrapper when Agent Harness installed one:

scripts/codex_emotion.sh status
scripts/codex_emotion.sh audit_state
scripts/codex_emotion.sh audit_log
scripts/codex_emotion.sh compact_log --dry-run
scripts/codex_emotion.sh record_policy --mode light --subject task --event-type work_checkpoint --memory-owner project "that migration was handled well"
scripts/codex_emotion.sh configure --style "warm but not over-compliant, with clear boundaries"
scripts/codex_emotion.sh tune "make it calmer"

If the target only has this skill folder and no project wrapper, use:

.codex/skills/emotion-engine-codex/scripts/codex_emotion.sh status

MCP is optional. Use it when a local MCP-capable client should expose Emotion Engine as native tools instead of shell commands. Register the bundled stdio server with the same Codex state file used by the wrapper:

python3 .codex/skills/emotion-engine-codex/scripts/emotion_engine_mcp.py --state .emotion-engine/codex-state.json --locked-state --managed-runtime

For local client setup, prefer the registration helper:

python3 .codex/skills/emotion-engine-codex/scripts/register_mcp_client.py codex --project-dir . --state-profile codex

Read the full file on GitHub · 248 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 248 lines · 30 tokens per session scan A acc2749d8105

Subscribe to this mod's changes

emotion-engine-codex is a skill published in the GitHub repository pioneerjeff-labs/emotion-engine (24 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 2,699 once invoked, about $0.0002 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.