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/gix9303/everos-codex/everos-local-memorynpx skills add gix9303/EverOS-Codex --skill everos-local-memorygit clone --depth 1 https://github.com/gix9303/EverOS-CodexWrote 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/gix9303/everos-codex/everos-local-memory)<a href="https://agentmods.dev/skills/gix9303/everos-codex/everos-local-memory"><img src="https://agentmods.dev/badge/skills/gix9303/everos-codex/everos-local-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 5.1 | $0.00055 | $0.00714 |
| Opus 5 | $0.00028 | $0.00357 |
| Sonnet 5 | $0.00011 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
everos-local-memory 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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EverOS Local Memory
Use this skill when Codex should rely on the local EverOS MCP memory layer rather than ad hoc recap in chat.
This skill is intentionally light. It does not replace the MCP bridge or EverOS service. It only fixes usage discipline so memory stays clean and useful over time.
Default path
Treat local EverOS as the long-term memory store and the MCP tools as the access layer:
memory_search: default recall entrypointmemory_save_turn: save a high-value task summarymemory_get: deterministic browse or read-your-write verificationmemory_flush: manual extraction trigger when needed
Default recall path is owner_type=user unless there is a clear reason to inspect agent_case or agent_skill.
Project discipline
Always prefer explicit project_id.
- Do not rely on one global default project unless the user explicitly wants a shared bucket.
- Keep different repos or systems in separate
project_idspaces. - If the user did not specify a project and the task is repo-specific, use the repo-derived default
project_idwhen available and state it briefly.
Recommended shape:
- one durable
project_idper repo or per product - temporary smoke tests only in dedicated test projects
- current MCP behavior can auto-infer the repo name as
project_id, but explicitproject_idstill wins
Search discipline
Start with memory_search when:
- the user asks what was done before
- the task mentions previous fixes, historical decisions, or prior context
- the current problem looks similar to an earlier one
Search rules:
- keep queries short
- prefer keywords or one short phrase
- start with
owner_type=user - only switch to
owner_type=agentwhen the target is explicitly about reusable agent cases or skills
Save discipline
Use memory_save_turn only for high-value summaries.
A good summary should usually contain:
- problem
- root cause
- fix
- verification
Optional but useful:
- title
- keywords
- explicit
project_id
What ships with it
1 file 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.
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.
- 5d ago First seen · 108 lines · 55 tokens per session scan A 7a97662e5a08
everos-local-memory is a skill published in the GitHub repository gix9303/EverOS-Codex (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 714 once invoked, about $0.0003 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…