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 Filipe-Soares-de-Almeida/MemAI --skill memai-linkgit clone --depth 1 https://github.com/Filipe-Soares-de-Almeida/MemAIWrote 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/filipe-soares-de-almeida/memai/memai-link)<a href="https://agentmods.dev/skills/filipe-soares-de-almeida/memai/memai-link"><img src="https://agentmods.dev/badge/skills/filipe-soares-de-almeida/memai/memai-link/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/filipe-soares-de-almeida/memai/memai-link"><img src="https://agentmods.dev/badge/skills/filipe-soares-de-almeida/memai/memai-link.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 | $0.00176 | $0.01807 |
| Opus 5 | $0.00088 | $0.00903 |
| Sonnet 5 | $0.00035 | $0.00361 |
| Haiku 4.5 | $0.00018 | $0.00181 |
Grade A, and why
memai-link 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memai-link — stitching the memory graph
Creates the edges that make the store navigable. It only relates: when a pair is the same thing, that is a merge and goes to [[memai-distill]].
1. Relation vocabulary (keep it consistent)
relation_type |
When it applies |
|---|---|
supersedes |
A replaces or retires B — a new version → the old one, a kept checkpoint → the archived one. Lineage. |
relates_to |
Complementary, the same subject, or the same phenomenon from another angle. The default. |
contradicts |
A and B claim incompatible things — pair it with the contradicted confidence of [[memai-confidence]]. |
links_to |
A generic pointer when none of the above fits. |
link_memoriestakesrelation_typeas free text — nothing rejects a fifth spelling. Write one of those four.
2. What is worth linking
- Materialize
[[wikilinks]]. A body that cites[[slug]]and has no edge in the graph gets arelates_to: a note on the queue drain whose text points at[[cache-warmup-cold-start]]reads as a link and is not one until the edge exists. - Complementary memories under one domain. Two notes filed in
acme/x100, one on the batch retry and one on the queue drain it re-enqueues into, that nobody ever connected. - checkpoint → note lineage. A kept checkpoint → the canonical note for
the mechanism (
relates_to); an archived checkpoint from a finishedproj-1042→ the note that inherited its durable content (relates_to). - Succession. A superseded memory → the one that stayed (
supersedes).distillalready links its new memorysupersedesto every source it archives — do not stage those again.
An edge is not the only stitch. When N memories are steps of one end-to-end process and none of them is the parent of the others, a mesh of
relates_tois the wrong repair: cross-list the N into the process path (omni/x900), and a single read scoped there returns them all, subtree included. That is thecrosslistkind and it belongs to the orchestrator — hand it to [[memai-maintenance]] instead of weaving the mesh.
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 · 134 lines · 176 tokens per session scan A 9afe940d9785
memai-link is a skill published in the GitHub repository Filipe-Soares-de-Almeida/MemAI (0 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 1,807 once invoked, about $0.0009 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
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
ask-user-question
Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
memos-memory-guide
Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query…
memmachine-memory
Use when an agent or model needs durable project, user, or session context from MemMachine, needs to save information to MemMachine memory, has requests involving mem-cli, memmachine, or memmachineclient, has insufficient conversation context, or is tempted to search local files for prior context that should come from…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.