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 skillmds/skillmd --skill cloud-syncgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/cloud-sync)<a href="https://agentmods.dev/skills/skillmds/skillmd/cloud-sync"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/cloud-sync/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/skillmds/skillmd/cloud-sync"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/cloud-sync.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 | $0.00064 | $0.01959 |
| Opus 5.5 | $0.00026 | $0.00784 |
| Sonnet 5 | $0.00013 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade C, and why
cloud-sync scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
skill is a thin front-end — check status, and on first run collect credentials, Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://127.0.0.1:${PORT}/api/sync/status" How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Sync (cmem.ai Pro)
The worker syncs memories itself: every write nudges a background flusher that drains unsynced rows to cmem.ai. There is no daemon to install or babysit. This skill is a thin front-end — check status, and on first run collect credentials, retire the old standalone client, and restart the worker so it picks them up.
Security rule for this entire skill: NEVER print the sync token, never put it in a command-line argument (argv is visible to other processes), and never log it. It travels only inside heredoc-fed stdin scripts or files that already hold it. When confirming, report its length — not its value.
1. Check status
Resolve the worker port (env → ~/.claude-mem/settings.json → per-UID default
37700 + (uid % 100), matching how the worker picks its own port; re-run this
in any fresh shell before the curls in step 5):
PORT="${CLAUDE_MEM_WORKER_PORT:-$(node -e "const fs=require('fs'),p=require('path'),os=require('os');const uid=(typeof process.getuid==='function'?process.getuid():77);const fallback=String(37700+(uid%100));try{const s=JSON.parse(fs.readFileSync(p.join(os.homedir(),'.claude-mem','settings.json'),'utf-8'));process.stdout.write(String(s.CLAUDE_MEM_WORKER_PORT||fallback));}catch{process.stdout.write(fallback);}" 2>/dev/null)}"
curl -s "http://127.0.0.1:${PORT}/api/sync/status"
Responses:
{"configured": true, "deviceId": ..., "pending": {"observations": N, "summaries": N, "prompts": N}, "lastFlushAt": ..., "lastError": ...}→ go to step 2.{"configured": false}→ go to step 3.- 404 / 503 / connection refused → the route registers late during worker startup, so a request right after a restart can miss it. Retry every 3s for ~15s before concluding anything. If 404 persists, the running worker predates cloud sync — restart it with the command in step 5, wait, and retry.
2. Already configured → report and stop
Report the three pending counts, lastFlushAt, and lastError (null means
healthy). Pending counts near 0 mean the cloud copy is current. Done — do not
run the setup steps below.
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.
- 4d ago First seen · 164 lines · 64 tokens per session scan C 4cefa474fb9e
cloud-sync is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,959 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.