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 skills/dannykkh/skill-olympus/codex-mnemonpx skills add Dannykkh/skill-olympus --skill codex-mnemogit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/skills/dannykkh/skill-olympus/codex-mnemo)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/codex-mnemo"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/codex-mnemo.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 | $0.00092 | $0.01516 |
| Opus 5 | $0.00046 | $0.00758 |
| Sonnet 5 | $0.00018 | $0.00303 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
codex-mnemo 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 today.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex-Mnemo - Codex CLI 기억 시스템
기억의 여신 Mnemosyne에서 유래. Claude Code용 Mnemo를 Codex CLI에 이식.
Codex CLI 세션 간 컨텍스트 유지를 위한 장기기억 시스템입니다.
설치
node skills/codex-mnemo/install.js # 설치
node skills/codex-mnemo/install.js --check # 설치/notify 진단
node skills/codex-mnemo/install.js --uninstall # 제거
Claude Code Mnemo와의 차이
| Claude Code (Mnemo) | Codex CLI (Codex-Mnemo) | |
|---|---|---|
| 훅 | 2개 (UserPromptSubmit + Stop) | 1개 (notify: agent-turn-complete) |
| 데이터 전달 | stdin JSON + transcript JSONL 파싱 | notify payload(JSON) (argv/stdin/파일경로 모두 처리) |
| 설정 | settings.json (JSON) | config.toml (TOML) |
| 규칙 파일 | CLAUDE.md | AGENTS.md |
| 저장 경로 | conversations/*-claude.md |
conversations/*-codex.md |
| 중복 방지 | 타임스탬프 기반 | turn-id 기반 (더 정확) |
핵심 원칙
| 원칙 | 설명 |
|---|---|
| 빠르게 | 기본은 훅에서 AI 호출 금지. 단, Chronos auto-continue는 예외 체인 |
| 단순하게 | 파일 기반, DB 없음 |
| 검색 가능하게 | 키워드 + 동의어 확장 |
포함 파일
codex-mnemo/
├── SKILL.md # 이 파일
├── install.js # 설치/제거 스크립트
├── hooks/
│ ├── save-turn.ps1 # Windows notify 오케스트레이터 (+ Chronos optional chain)
│ ├── append-user.ps1 # User 저장 전담
│ ├── append-assistant.ps1 # Assistant 저장 전담
│ ├── save-turn.sh # Linux/Mac notify 오케스트레이터 (+ Chronos optional chain)
│ ├── append-user.sh # User 저장 전담
│ └── append-assistant.sh # Assistant 저장 전담
├── scripts/
│ └── reconcile_codex_conversations.py # rollout JSONL → conversations/ 복구
└── templates/
└── agents-md-rules.md # AGENTS.md 주입 규칙
Reconcile (누락 턴 복구)
Codex의 notify 훅이 한 번이라도 실패하거나 Codex CLI가 강제 종료되면 해당 턴의
conversations/YYYY-MM-DD-codex.md 미러링이 유실됩니다. 그러나 rollout JSONL
(<CODEX_HOME>/sessions/YYYY/MM/DD/rollout-*.jsonl)은 Codex가 직접 기록하는 source of truth
이므로, reconcile_codex_conversations.py가 이를 스캔해 누락된 turn을 자동 복구합니다.
여기서 <CODEX_HOME>은 CODEX_HOME 환경 변수 값이며, 미설정 시 ~/.codex입니다.
What ships with it
13 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.
- hooks/append-assistant.ps1 576 B runs code
- hooks/append-assistant.sh 273 B runs code
- hooks/append-user.ps1 550 B runs code
- hooks/append-user.sh 240 B runs code
- hooks/codex-hook-bridge.js 13 KB runs code
- hooks/save-turn.ps1 30 KB runs code
- hooks/save-turn.sh 19 KB runs code
- hooks/sync-sessions.ps1 6.2 KB runs code
- install.js 27 KB runs code
- scripts/reconcile_codex_conversations.py 58 KB runs code
- scripts/tests/install-check.test.js 1.6 KB runs code
- scripts/tests/test_reconcile_codex_conversations.py 23 KB runs code
- templates/agents-md-rules.md 28 KB
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.
- today Changed 88a490cae280
- 4d ago First seen · 128 lines · 92 tokens per session scan A 248a429ff551
codex-mnemo is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 1,516 once invoked, about $0.0005 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 skills, from other repositories
context-management
Project context loading, isolation, and persistent state management across CCPM sessions.
session-memory
Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
context-engineering
Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on demand, sizing an install or an always-loaded file, fixing an agent that drifts, repeats itself, or forgets constraints mid-task, planning compaction or summarization…
context-optimizer
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
kb-answer
Answer questions using your project's knowledge base with evidence-backed citations. Every answer must cite literal quotes from KB files to prevent hallucinations. Use this for any question that should be answered from documented knowledge rather than general knowledge.