bb is an agentic IDE that lets users control, customize, and automate a software-development environment through a desktop app, web app, command-line interface, or HTTP API. Developers use it to run work in observable threads that can be steered or handed off to other agents. Its catalogue add-ons provide skills and instructions for working with bb.
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 get-bb/bb --skill share-server-linksgit clone --depth 1 https://github.com/get-bb/bbWrote 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/get-bb/bb/share-server-links)<a href="https://agentmods.dev/skills/get-bb/bb/share-server-links"><img src="https://agentmods.dev/badge/skills/get-bb/bb/share-server-links/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/get-bb/bb/share-server-links"><img src="https://agentmods.dev/badge/skills/get-bb/bb/share-server-links.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.00901 |
| Opus 5.5 | $0.00008 | $0.00360 |
| Sonnet 5.5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
share-server-links 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 21d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Share local server links via bb connect
When you start an HTTP server the user should open, give them a connect share URL — not a localhost URL. Shares work from threads running on any enrolled host, and the command resolves the thread's host automatically.
- Check remote access: run
bb connect status --json. Ifpairedis false, give the localhost URL and mention that remote URLs work once this bb is signed in to its bb account (bb account login). Ifenabledis false, the user turned remote access off withbb connect off; give the localhost URL and mentionbb connect on. Don't turn it on or sign in yourself unless the user asks. - From the thread that started the HTTP server, run
bb connect expose <port>. It prints that host's share URL. Use--host <name-or-id>only when you intentionally need another enrolled host; outside a thread, sharing defaults to the machine running the bb server. - Give the returned URL to the user as a markdown link. It works for viewers who have the owner's getbb.app session; it is not a public internet link.
- When the server stops, run
bb connect unexpose <port>from the same thread (or with the same--host) so the share is cleaned up. Usebb connect shares [--host <name-or-id>]to inspect that host's shares.
Use bb connect unexpose-all [--host <id>] [--json] to revoke all shared ports
on one machine, including an unavailable machine. It defaults to the thread's
machine, or the server machine outside a thread, and keeps machine pairing intact.
Each collapsible machine group in settings offers Revoke all for that machine.
The typed plugin RPC is unexposeAll with { hostId: string } input and a
{ removed: number } result. Bulk revocation attempts every share on that
machine; any failures report partial progress and can be retried.
bb connect --help and bb connect <command> --help print the commands and
their flags and exit 0. Unknown commands and flags fail with a suggestion —
bb connect list points at bb connect shares — and with --json a failure
prints {"ok":false,"error":{"code":…,"message":…}} on stdout while the same
message stays on stderr.
Server-host shares use https://<server-label>--<port>.<base-domain> through
the server tunnel. Other enrolled hosts use
https://<machine-label>--<port>.<base-domain> through their daemon. If a
machine was not enrolled through Connect, expose fails with instructions to
remove and re-add it under Settings > Machines.
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.
- 21d ago Changed · +24 lines 734345f687cd
- 1mo ago Changed · +6 lines a288b79890eb
- 1mo ago Changed · +9 lines 6c779f85ffb5
- 1mo ago Changed · -69 tokens per session cccfad03370e
- 1mo ago First seen · 30 lines · 90 tokens per session scan A fbb3aee45ccb
share-server-links is a skill published in the GitHub repository get-bb/bb (4,515 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 901 once invoked, about $0.0001 per session on Opus 5.5. 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
mirrord-db-branching
Helps users configure mirrord.json for database branching, enabling isolated database copies for safe development and testing. Use when the user wants to set up MySQL, MariaDB, PostgreSQL, MSSQL, MongoDB, Redis, DynamoDB, ClickHouse, Google Spanner, Amazon S3, turbopuffer, or generic branches, configure copy modes…
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
mirrord-header-propagation
Makes a codebase propagate W3C baggage (the baggage header carrying mirrord-session= ) end to end, so mirrord HTTP filters, preview environments, and queue splitting can route a whole request chain to one developer's session. Detects existing OpenTelemetry, Datadog, or other tracing that can already propagate baggage…
mirrord-kafka
Helps DevOps engineers configure mirrord Operator's Kafka queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs (the current resources; MirrordKafkaTopicsConsumer + MirrordKafkaClientConfig are deprecated but still supported), the matching mirrord.json…
mirrord-operator
Help users install and configure the mirrord Operator for team/enterprise environments. Use when users ask about operator setup, Helm installation, cloud API key or license configuration, air-gapped/offline licensing, enabling features (queue splitting, DB branching, preview environments, multi-cluster), internal…
mirrord-temporal
Helps DevOps engineers configure mirrord Operator's Temporal task queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs, the matching mirrord.json splitqueues section with messagefilter and jqfilter, and Helm value guidance. Use this skill whenever the user…