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/pinnpx skills add mubit-ai/claude-plugins --skill pingit clone --depth 1 https://github.com/mubit-ai/claude-pluginsWrote 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/mubit-ai/claude-plugins/pin)<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/pin"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/pin.svg" alt="Measured on agentmods" 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 | $0.00110 | $0.01539 |
| Opus 5 | $0.00055 | $0.00770 |
| Sonnet 5 | $0.00022 | $0.00308 |
| Haiku 4.5 | $0.00011 | $0.00154 |
Grade A, and why
pin 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 5d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill never installs anything. It runs one Node process from the plugin directory, which writes a run-scoped variable to the user's own Mubit instance. No packages, no services, no changes to the shell.
What a pin is
A pin is a sentence that is true for this run and this task, injected in full above the recalled memory on every prompt until it is cleared.
for the rest of this, don't touch the vendored server
The model is who notices a sentence like that. Before pinning existed, the only place to put it was memory — so it was written as a lesson, and a lesson is durable and cross-session. It would then be recalled into every future session of a project where it had long since stopped being true. Removing that failure is the entire reason this command exists.
Pin or remember — the line is not blurry
/mubit-memory:pin |
/mubit-memory:remember |
|
|---|---|---|
| Scope | this run, this task | durable, every future session |
| Ends when | the user clears it, or the run does | never, unless it is forgotten or superseded |
| Costs | tokens on every prompt of this run | nothing until recall decides it is relevant |
| Example | "no new dependencies while we finish this PR" | "this project pins dependencies by exact version" |
Read the two example rows before choosing. If the sentence would still be worth saying in six
months, in a different session, it is a lesson — use /mubit-memory:remember. If it would be
wrong to say next week, it is a pin.
Pin something
node "${CLAUDE_PLUGIN_ROOT}/bin/pin.mjs" add "don't touch the vendored server" --run <run_id> --json
It renders on the very next prompt — the command writes through to the local cache the recall hook reads, so there is nothing to wait for.
Use the user's own words. A pin is an instruction, and paraphrasing an instruction changes it.
Always pass --run
<run_id> is the run named in the Mubit memory is active block at the top of this
conversation — the line reading Run: cc-<slug>-<hash>. Copy it verbatim.
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.
- 5d ago First seen · 119 lines · 110 tokens per session scan A a71b97406df4
pin is a skill published in the GitHub repository mubit-ai/claude-plugins (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 110 tokens to every session and 1,539 once invoked, about $0.0006 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.