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/memtensor/memmy-agent/update-setupnpx skills add MemTensor/memmy-agent --skill update-setupgit clone --depth 1 https://github.com/MemTensor/memmy-agentWhat 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 | $0.00032 | $0.01284 |
| Opus 5 | $0.00016 | $0.00642 |
| Sonnet 5 | $0.00006 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
update-setup 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Setup
Generate a personalized upgrade skill for this workspace.
Step 1: Check Existing
Use read_file to check if skills/update/SKILL.md already exists in the workspace.
If it exists, ask the user: "An upgrade skill already exists. Reconfigure?" Wait for the user's reply. If no, stop here.
Step 2: Current Version and Install Clues
Use exec to run memmy --version. Tell the user the current version.
Then collect install clues with exec. These commands are best-effort; if one fails,
keep going and show the useful output:
command -v memmy || true
npm list -g memmy-agent --depth=0 || true
pnpm list -g memmy-agent --depth=0 || true
yarn global list --pattern memmy-agent || true
Summarize what you found in one short paragraph. Use the clues only to suggest a likely install method. Do not treat them as confirmation.
Step 3: Confirm Required Inputs
CRITICAL: Do not write skills/update/SKILL.md until the install method is
explicitly confirmed by the user. The install method must come from a user
answer or confirmation, not from inference alone. If you cannot get a clear
answer, stop and ask the user to rerun this setup when they know how memmy was
installed.
Treat a request like "generate upgrade config", "set up updates", or "use
update-setup" as the goal, not as confirmation of the install method. Install
clues are only hints for the question summary; never choose npm, pnpm,
yarn, or source from clues alone. In the initial setup turn, write
skills/update/SKILL.md only if the user message already contains an explicit
install method and proxy answer. Otherwise, ask Question 1 and stop.
Hard stop rule: after collecting install clues without an explicit install
method from the user, do not call write_file for any path ending in
skills/update/SKILL.md in that same assistant turn. This remains true when
update-setup is part of a larger task that also creates other skills or runs
external installers. Finish the safe parts, ask Question 1, and wait for a later user
message before continuing.
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.
- 2d ago First seen · 128 lines · 0 tokens per session scan A ae7cf948da03
update-setup is a skill published in the GitHub repository MemTensor/memmy-agent (1,190 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,284 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
release
Cut a versioned release and publish everos to PyPI via the tag-triggered workflow.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground…