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 codex-providergit 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/codex-provider)<a href="https://agentmods.dev/skills/get-bb/bb/codex-provider"><img src="https://agentmods.dev/badge/skills/get-bb/bb/codex-provider/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/codex-provider"><img src="https://agentmods.dev/badge/skills/get-bb/bb/codex-provider.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 | $0.00020 | $0.00695 |
| Opus 5.5 | $0.00008 | $0.00278 |
| Sonnet 5.5 | $0.00004 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
codex-provider 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.
What it actually says
Codex provider
Codex supports structured plan requests, editing and rerunning eligible messages,
and compaction through the corresponding core bb thread commands.
bb thread clear-goal <id> clears its durable active Goal and waits for provider
confirmation. Inspect the thread before recovery actions.
Codex questions from request_user_input pause the turn until answered.
Questions from request_user_input_async do not pause it: the plugin opens a
question card for each one that stays open for up to an hour after the turn
ends. Submitting sends the answer to the thread as a message
(steering an active turn or starting a new one); dismissing sends nothing.
From the CLI, find it with bb thread interactions list <thread> and answer
with bb thread interactions respond <interactionId> <thread> --value '{"answers":{"question-1":{"selected":["option-2"]}}}'. Questions and options
are numbered from 1 in order; use "freeText" for a typed answer.
Unlisted model IDs are accepted by this provider; acceptance does not establish
account access. Inspect models on the actual execution host with
bb provider models codex using the machine or environment selector.
Service tiers are default, fast, and ultrafast. Codex reports the tiers
each model accepts for the signed-in account, so the model picker and
bb provider models codex (Service tiers column, supportedServiceTiers in
--json) list Ultrafast only for eligible models and accounts. Pass the id to
--service-tier on bb thread spawn or bb thread tell; bb sends an explicit
tier to Codex as given. When the model does not list it, Codex runs the turn
at its default tier and the thread shows its warning that the tier "is not
advertised as supported" and was omitted.
Daybreak is a session option with the id daybreak, offered only when the
signed-in account's model list advertises a Daybreak program. Turn it on in the
model picker, with bb thread spawn --option daybreak=true, or on an existing
thread with bb thread options --set daybreak=true; it applies from the next
turn and Codex stores the choice on its own thread. With it on, each turn asks
for the selected model's Daybreak program (blue when the model lists it,
otherwise red); once it has been turned off, each turn asks for the standard
program. A thread where Daybreak was never set sends no program and leaves the
choice to Codex.
bb provider models codex lists the option, and --json shows per model
whether it runs with Daybreak, without it, or both (sessionOptions, where
fixed: true means only the listed value). A model that cannot run in the
current state is disabled in the picker. The gpt-daybreak-*-latest alias
models leave the main list when the switch is available and stay selectable
only on threads that already use them.
Use the core CLI skill for command syntax and official Codex guidance for upstream product behavior.
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 Changed · +16 lines a2a9df40d68f
- 6d ago Changed · +10 lines 529543a7f3fd
- 13d ago Changed · +9 lines ddabf382c124
- 1mo ago First seen · 19 lines · 20 tokens per session scan A 0bb74562812f
codex-provider is a skill published in the GitHub repository get-bb/bb (4,324 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 695 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 2026-09-07.
Other skills, from other repositories
using-grove
Use when orchestrating Grove workspaces from outside, including creating or supervising host or container agents, steering a fleet, using Grove CLI or MCP tools, or having agents write to each other through the mailbox. Also use when splitting work across workspaces, reviewing a diff from several angles, managing…
working-in-grove
Use when working inside a Grove workspace, including reporting task phase, updating a workspace or its ticket links, using GROVEPHASEFILE, writing to another Grove agent through the mailbox, or waiting on slow work like CI by registering a watch instead of sleeping. Also use when a worktree has a phase file, when…
collaborating-on-diagrams
Use when working with an existing .drawio diagram through Grove collaboration. Triggers on opening, reading, editing, updating, stopping, or recovering a diagram in a Grove workspace. Covers revisioned managed writes, XML-preserving edits, collaboration state, conflicts, read-only stop, and container/editor limits.
mocking-up-in-grove
Use when a visual or frontend task in a Grove workspace needs a mockup approved before code — a new control, a redesigned surface, a layout change. Covers drawing a draw.io mockup through Grove's diagram tools, previewing it in the browser, getting sign-off, filing the approved image on the tracker issue, and handing…
leading-in-grove
Use when you lead a fleet of Grove teammates toward one deliverable, including deciding how many to spawn and how to split the work, writing their onboarding prompt, getting acknowledgment, running scheduled check-ins, answering their mailbox questions, keeping tickets and your own status compaction-proof, reviewing…
configuring-grove
Use when configuring Grove for a user or project, including agent rosters, init scripts, containers, private credentials, daemon or MCP setup, or the native-versus-terminal launch of a Claude Code or Codex agent. Also use when resolving config layers, validating a config schema, or explaining why a workspace starts…