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/evermind-ai/everme/everme-memorynpx skills add EverMind-AI/EverMe --skill everme-memorygit clone --depth 1 https://github.com/EverMind-AI/EverMeWrote 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/evermind-ai/everme/everme-memory)<a href="https://agentmods.dev/skills/evermind-ai/everme/everme-memory"><img src="https://agentmods.dev/badge/skills/evermind-ai/everme/everme-memory.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 | $0.00091 | $0.01297 |
| Opus 5 | $0.00046 | $0.00648 |
| Sonnet 5 | $0.00018 | $0.00259 |
| Haiku 4.5 | $0.00009 | $0.00130 |
Grade B, and why
everme-memory scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.codex/config.toml::mcp_servers.everme` (auto-managed by How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EverMe Memory (Codex)
This skill connects you to EverMe's persistent memory across sessions.
How memory reaches you on Codex
EverMe lifecycle hooks work independently of the model-facing tool surface:
SessionStartinjects the user's profile.UserPromptSubmitsearches and injects relevant memory.Stopsaves the latest completed turn and flushes every five turns.PreCompactflushes pending extraction before compaction.
These hooks are fail-open: a memory backend error never blocks Codex. The MCP server remains available for explicit reads and writes chosen by the model.
Codex variants differ in what the LLM-facing tool layer surfaces:
- Codex App (the desktop GUI, observed v0.128/v0.133) — the LLM
layer routinely exposes MCP Resources (
list_mcp_resources/read_mcp_resource); MCP Tools (tools/call) are visible in the/mcppanel but typically NOT exposed to the LLM as callable functions. - Codex CLI (the
codexterminal command) — has been observed to expose both Resources and Tools to the LLM in practice.
The memory server is configured under
~/.codex/config.toml::mcp_servers.everme (auto-managed by
evercli plugin install codex).
Two URIs are available:
| URI | What it returns | When to read |
|---|---|---|
mem://profile |
The user's durable Profile ONLY (preferences, habits, traits, long-term decisions), rendered as markdown. It never performs semantic search and never contains episodes, raw messages, or agent cases/skills. | Once at the start of a conversation when no <everme_profile> block was injected. Do not use it as a fallback for recalling past decisions or task context — that is mem://search's job. |
mem://search?q={query}&topK={topK} |
Search results across episodic memories, profile entries, agent cases/skills, and the recent raw transcript, rendered as markdown (raw rows appear under a provisional unextracted-transcript header — never quote them as established facts). Keep q short — a few keywords or one short phrase, not a long passage; topK defaults to 10, omit it. |
When the user references prior context ("what did we say about X", "remember when…", "based on what we decided last week…", "did we fix this before") and the injected <everme_recall> block is missing, empty, or clearly unrelated. Do not repeat a search the recall block already answers, and do not repeat an identical query within the same turn. |
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.
- yesterday Changed · -11 lines 019b5207dd4e
- 5d ago First seen · 111 lines · 91 tokens per session scan B b04ee570a2fe
everme-memory is a skill published in the GitHub repository EverMind-AI/EverMe (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 91 tokens to every session and 1,297 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dashboard
Open OwnMem Console, the local dashboard for this repository's memory. Use when the user asks to open the dashboard, see memory metrics, check adoption or recall quality, or set up the optional embedding lane. Requires a repository initialized with the dashboard layer.
recall
Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
cargo-content
Manage the knowledge a Cargo workspace holds — upload files (PDF, CSV, text), rename and organize them, and build native or connector-backed libraries that sync from an external source, so agents can retrieve them (RAG). Triggers: "upload this PDF", "add these docs as knowledge", "build a knowledge base", "sync our…
immortal-skill
通用数字永生框架：从聊天记录、社交媒体、文档等多平台数据中蒸馏任何人的数字分身——支持自己、同事、导师、亲人、伴侣/前任、朋友、公众人物 7 种角色模板，接入国内外 12+ 数据平台。.
chen-yun-demo
蒸馏陈韵的全维度数字分身：产品设计方法、沟通风格、人生经历与价值观。仅用于个人备份与辅助回忆，非对外冒充。.