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/mubit-ai/claude-plugins/setupnpx skills add mubit-ai/claude-plugins --skill setupgit clone --depth 1 https://github.com/mubit-ai/claude-pluginsWhat 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 | $0.00038 | $0.01359 |
| Opus 5 | $0.00019 | $0.00679 |
| Sonnet 5 | $0.00008 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill never installs anything. It reads what is configured, tells the user exactly what is missing, and gives them the one place to fix it. Do not install packages, do not start services, do not write into their shell profile. A memory plugin that runs installers is a trust failure.
What a working setup looks like
Two values, and nothing else:
| Setting | Value |
|---|---|
endpoint |
the user's Mubit instance URL, e.g. https://api.mubit.ai |
apiKey |
a key of the form mbt_... |
If either is missing, run /mubit-memory:auth. It opens the console, signs the user in,
checks the key against the instance and stores it — which is the whole of what this skill would
otherwise ask them to do by hand. Do not walk somebody through the manual steps first.
The manual route still exists and still wins over what auth writes: /plugin → Mubit Memory →
configure puts the key in the OS keychain, which is the best place for it. Prefer that for a
long-lived install; prefer /mubit-memory:auth for getting someone working in the next minute.
Step 1 — read what is configured
Precedence, highest first: the plugin's endpoint and apiKey settings
(CLAUDE_PLUGIN_OPTION_*, where the keychain-backed key lives), then MUBIT_ENDPOINT /
MUBIT_API_KEY in the environment, then ${CLAUDE_PLUGIN_DATA}/credentials.json (what
/mubit-memory:auth writes), then ${CLAUDE_PROJECT_DIR}/.mubit-cc.json.
- No endpoint → there is nothing to talk to. Capture spools locally and recall returns
nothing; nothing is lost and nothing is sent. Point the user at the console, then at
/plugin→ configure. - No key → same destination. An endpoint without a key gets
auth_failedon every call.
Step 2 — confirm with mubit_status
A ready state, the expected endpoint echoed back, and a run id is a finished setup. Report
those three things and stop.
Anything else maps to one cause:
| Result | What it means | What to tell the user |
|---|---|---|
auth_failed |
The key is missing, wrong, or revoked. Not a network problem. | Run /mubit-memory:auth to sign in again. Nothing else in this skill helps. |
unreachable |
Nothing is listening at that address. | The endpoint is wrong, or the instance is not running. Check both in the console. |
warming |
The instance is still starting. | Wait and retry — this is not a failure. |
server_error |
The instance is up and failing. | Retry once, then check the instance's status in the console. The client cannot fix it. |
not_responding |
Three or more consecutive timeouts. | Usually load, not death. Retry before concluding anything. |
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 · 107 lines · 38 tokens per session scan A 3d94437ef768
setup is a skill published in the GitHub repository mubit-ai/claude-plugins (13 stars, last pushed 5d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,359 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…