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 provider-retrygit 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/provider-retry)<a href="https://agentmods.dev/skills/get-bb/bb/provider-retry"><img src="https://agentmods.dev/badge/skills/get-bb/bb/provider-retry/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/provider-retry"><img src="https://agentmods.dev/badge/skills/get-bb/bb/provider-retry.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 | $0.00017 | $0.00148 |
| Opus 5 | $0.00009 | $0.00074 |
| Sonnet 5 | $0.00003 | $0.00030 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
provider-retry 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.
What it actually says
Provider retry
The plugin is enabled on fresh installations. When a turn fails on a structured Codex or Claude Code subscription-window limit with a reset time, it queues the original input verbatim for after the window opens, marked agent-only.
A pending retry is an ordinary durable queued row and survives restart. Inspect
it with bb thread queue list <thread-id> and inspect the failed turn before
manually retrying it; avoid duplicating an existing queued retry.
Use the core bb thread retry command for an intentional manual retry. Follow
its live help for selection and scheduling flags.
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 · 18 lines · 17 tokens per session scan A 6ca735038c95
provider-retry is a skill published in the GitHub repository get-bb/bb (3,455 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 148 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
cradle-cli
Use whenever you need to read, inspect, wait on, or mutate Cradle-owned state or workflows, including issues, delegation, sessions, awaits, CI/review waits, timed waits, Work inspection, workspaces and git inspection, Chronicle, automations, usage, observability, skills, agents, profiles, providers, preferences…
cradle-observability-debugger
Debug Cradle local observability data by querying SQLite events/incidents/timeline, runtime snapshots, metrics, and server logs.
cradle-plugin-browser-use
Control Cradle's in-app browser via MCP tools. Use when the Claude Agent needs to navigate websites, click elements, type text, take screenshots, read page content, or inspect DOM structure within the Cradle desktop app's embedded browser panel. Triggers on "open URL", "navigate to", "click the button", "fill the…
cradle-artifacts
Use when creating or updating Cradle Agent Artifacts via writeartifact — interactive JSX dashboards, audits, review boards, charts, and tables rendered beside chat. Prefer this over dumping structured UI as markdown. Covers cradle/artifact imports, export default, component inventory, artifactId reuse, and…
cradle-plugin-development
Create, develop, debug, install, or update Cradle plugins built with @cradleapp/plugin-sdk. Use for Cradle server, web, or desktop plugin packages and Agent-authored personal plugins. Do not use for Codex .codex-plugin packages or one-off Cradle Artifacts.
cradle-design-system
Cradle visual language contract. Read CHEATSHEET.md before every UI task. Use for mockups, components, handoff, and token audits.