provider-retry

provider-retry is a skill for Claude Code, Codex from get-bb/bb. It costs 17 tokens per session (148 once invoked), scanned A, original, MIT.

A skill that queues a failed coding-agent turn for automatic retry after a provider subscription-window limit resets. A subscription window is a usage period imposed by the provider.

In plain words
What is it for?
Use it to inspect pending retries, check the failed turn, and avoid creating a second retry for the same request. It supports structured Codex and Claude Code failures with a reset time.
Why use it?
It prevents a temporary usage-limit failure from losing the original request or requiring a duplicate manual retry.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to inspect pending retries, check the failed turn, and avoid creating a second retry for the same request. It supports structured Codex and Claude Code failures with a reset time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/get-bb/bb/provider-retry
About the project

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.

get-bb/bb · 3,455 stars · on GitHub · getbb.app

Install

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.

Any agent
npx skills add get-bb/bb --skill provider-retry
Clone the repo
git clone --depth 1 https://github.com/get-bb/bb

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for provider-retry

README.md
[![agentmods](https://agentmods.dev/badge/skills/get-bb/bb/provider-retry/github.svg)](https://agentmods.dev/skills/get-bb/bb/provider-retry)
Your own site
<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.

agentmods 80×15 button for provider-retry

Your own site · 80×15
<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>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 6ca735038c95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

plugins/provider-retry/skills/provider-retry/SKILL.md · 18 lines

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.

Changes

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.

  1. 2d ago First seen · 18 lines · 17 tokens per session scan A 6ca735038c95

Subscribe to this mod's changes

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.

Related

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…

wibus-wee/cradle-app · 152 tokens

cradle-observability-debugger

Debug Cradle local observability data by querying SQLite events/incidents/timeline, runtime snapshots, metrics, and server logs.

wibus-wee/cradle-app · 33 tokens

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…

wibus-wee/cradle-app · 126 tokens

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…

wibus-wee/cradle-app · 67 tokens

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.

wibus-wee/cradle-app · 65 tokens

cradle-design-system

Cradle visual language contract. Read CHEATSHEET.md before every UI task. Use for mockups, components, handoff, and token audits.

wibus-wee/cradle-app · 35 tokens