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 skills add 234194027-cpu/aion-memory-nexus --skill life-memory-mcp-connectgit clone --depth 1 https://github.com/234194027-cpu/aion-memory-nexusWrote 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/234194027-cpu/aion-memory-nexus/life-memory-mcp-connect)<a href="https://agentmods.dev/skills/234194027-cpu/aion-memory-nexus/life-memory-mcp-connect"><img src="https://agentmods.dev/badge/skills/234194027-cpu/aion-memory-nexus/life-memory-mcp-connect/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.
<a href="https://agentmods.dev/skills/234194027-cpu/aion-memory-nexus/life-memory-mcp-connect"><img src="https://agentmods.dev/badge/skills/234194027-cpu/aion-memory-nexus/life-memory-mcp-connect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.02525 |
| Opus 5 | $0.00037 | $0.01262 |
| Sonnet 5 | $0.00015 | $0.00505 |
| Haiku 4.5 | $0.00007 | $0.00252 |
Grade A, and why
life-memory-mcp-connect 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 11d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Life Memory MCP Connect
Use this skill to onboard an agent into the Life Memory System through a portable stdio MCP bridge. Prefer the full automatic bootstrap script first; use the lower-level scripts only when the target environment needs custom control.
What This Gives Agents
Life Memory is the shared long-term memory layer for connected agents. It helps agents start with prior user/project context, avoid making the user repeat decisions, preserve useful task outcomes, and sync memories from other agent systems into one reviewable pipeline.
Use it as a habit loop:
- Read memory before substantial work.
- Search again when scope changes.
- Write a short task-end summary after work.
- Sync old memories once and daily deltas on a schedule.
Architecture
This skill has three layers:
- Skill layer: teaches an external agent how to install, configure, test, and operate the bridge.
- MAP layer:
memory_mapreturns the Memory Access Protocol: tool order, context fields, write rules, and daily sync strategy. - MCP layer: exposes concrete tools for search, before/after task hooks, event upload, daily delta sync, media upload, and smoke tests.
Graphiti/Neo4j, when enabled by an operator, is an internal, disposable retrieval projection. This Skill exposes no Graphiti write, replay, administration, or cross-project tool; if Graphiti is disabled or unavailable, the existing retrieval chain remains the source of MCP results.
After a client connects, call memory_map before other memory tools. Use references/memory-access-map.md when you need the complete operating contract.
For copy-paste onboarding, use references/agent-bootstrap-prompt.md. Keep that prompt short: it should only start the bootstrap flow, while detailed operating rules live in this skill, references/memory-access-map.md, and the live memory_map tool response.
For Codex on Windows or RTK environments, read references/windows-codex-troubleshooting.md before writing config or debugging sync failures.
For recurring sync setup, use references/automation-templates.md.
What ships with it
16 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.
- agents/openai.yaml 342 B
- references/agent-bootstrap-prompt.md 719 B
- references/auto-submit-policy.md 1.1 KB
- references/automation-templates.md 2.0 KB
- references/mcp-config-examples.md 1.4 KB
- references/memory-access-map.md 6.1 KB
- references/windows-codex-troubleshooting.md 2.6 KB
- scripts/bootstrap_life_memory_agent.py 4.1 KB runs code
- scripts/configure_mcp.py 2.4 KB runs code
- scripts/doctor.py 2.8 KB runs code
- scripts/install_life_memory_skill.py 8.3 KB runs code
- scripts/life_memory_mcp_server.py 26 KB runs code
- scripts/mcp_contract.json 22 KB
- scripts/smoke_test_mcp.py 8.7 KB runs code
- scripts/validate_memory_batch.py 4.1 KB runs code
- scripts/write_codex_mcp_config.py 4.2 KB runs code
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.
- 11d ago First seen · 221 lines · 75 tokens per session scan A 1018f9bae4fa
life-memory-mcp-connect is a skill published in the GitHub repository 234194027-cpu/aion-memory-nexus (0 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,525 once invoked, about $0.0004 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
engrama-onboard
Build a personalized Engrama memory graph for any user through a conversational interview. Use this skill whenever someone says "set up Engrama", "create my graph", "onboard", "build my profile", "configure Engrama for me", or asks how to start using Engrama. Also use when the user mentions they have a different role…
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…