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-checkpointsgit 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-checkpoints)<a href="https://agentmods.dev/skills/filipe-soares-de-almeida/memai/memai-checkpoints"><img src="https://agentmods.dev/badge/skills/filipe-soares-de-almeida/memai/memai-checkpoints/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-checkpoints"><img src="https://agentmods.dev/badge/skills/filipe-soares-de-almeida/memai/memai-checkpoints.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 | $0.00162 | $0.02396 |
| Opus 5 | $0.00081 | $0.01198 |
| Sonnet 5 | $0.00032 | $0.00479 |
| Haiku 4.5 | $0.00016 | $0.00240 |
Grade A, and why
memai-checkpoints 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memai-checkpoints — the lifecycle of a checkpoint
A checkpoint is a bearing summary — where the work stands — transient and
replaced as the work moves on ([[memai-memory]] §5). The durable knowledge
lives in note/reasoning/anti_pattern. This skill keeps only the bearing
still needed and retires the rest without losing knowledge: if the
durable part is not in a note yet, it goes there first ([[memai-distill]]).
This skill does not curate
note. Onlytype=checkpointrecords enter here.
It proposes; it does not apply. Everything below is staged through
optimize_stageand applied or rejected by the human in the dashboard. The destructive kinds it can stage —archiveanddistill— are rejected without a non-emptyverifieddescribing the live-facts check behind them.
1. The state of the work is declared by the project
Every decision below turns on whether the work a checkpoint is the bearing for is live, paused or closed. That state is not in the store: MemAI records where the work stood, not whether it is still open.
So read it from whatever the host project declares as its source of truth
for the state of work — a section of its own CLAUDE.md, an issue tracker, the
branch and the git log, a status file the project keeps. This skill reads that
source; it never infers the state from a checkpoint's own wording, from its
age, or from a domain having gone quiet. Establish what the source is before
the first decision, and take what it says as the state.
The checkpoint's domain is what joins it to that work. A ticket or issue is
one segment — proj-1042, where the hyphen is not a level
([[memai-memory]] §2.1) — so it can be the whole path or sit inside one
(proj-1042/p200), and a filter on proj-1042 covers the subtree either way.
| State of the work | Decision on its checkpoints |
|---|---|
| Closed | archive — but only after confirming with search/recall that the durable part is already in a note. If it is not, do not stage the archive: running standalone, apply [[memai-distill]]'s logic (distill, or note() directly) to save the lesson FIRST, or hold the archive and report the checkpoint as "durable pending". Never archive knowledge away because a distill pass has not run. |
| Live / paused | Keep the most recent (created_at DESC) as the bearing. Archive the intra-session trail behind it, each with a supersedes link → the one kept (§4). |
| Not declared — the project names no source of truth, or its source does not mention this work | Keep the most recent and report the rest as a question for the human: is this still open, or delivered and waiting to be closed? Stage nothing destructive. Do not invent a state. |
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 · 160 lines · 162 tokens per session scan A 18d975dfaee9
memai-checkpoints is a skill published in the GitHub repository Filipe-Soares-de-Almeida/MemAI (0 stars, last pushed today), licensed MIT. It adds 162 tokens to every session and 2,396 once invoked, about $0.0008 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.