bb-agent-coordination

bb-agent-coordination is a skill for Claude Code, Codex from nweii/agent-stuff. It costs 45 tokens per session (855 once invoked), scanned A, original, MIT.

A set of working rules for coordinating coding-agent tasks across bb threads, which are separate shared work conversations. It covers delegation, ownership, reports, review, and handoff, while bb-cli provides the commands.

In plain words
What is it for?
Use it to split work across bb threads, define task boundaries, review thread reports, reconcile changes, and hand work back to a coordinator.
Why use it?
It reduces confusion about who owns each task, which environment may be changed, and how completed work should be checked and combined.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nweii/agent-stuff/bb-agent-coordination
Any agent
npx skills add nweii/agent-stuff --skill bb-agent-coordination
Clone the repo
git clone --depth 1 https://github.com/nweii/agent-stuff

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 bb-agent-coordination

README.md
[![agentmods](https://agentmods.dev/badge/skills/nweii/agent-stuff/bb-agent-coordination.svg)](https://agentmods.dev/skills/nweii/agent-stuff/bb-agent-coordination)
Your own site
<a href="https://agentmods.dev/skills/nweii/agent-stuff/bb-agent-coordination"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/bb-agent-coordination.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00855
Opus 5 $0.00023 $0.00428
Sonnet 5 $0.00009 $0.00171
Haiku 4.5 $0.00005 $0.00085

Measured 3d ago against content hash 2fcd9a7621f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bb-agent-coordination 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 3d 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.

skills/bb-agent-coordination/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bb agent coordination

Read and follow the managed bb-cli skill before operating bb. It owns current commands, thread lifecycle, environment behavior, and result inspection. This skill owns task contracts, work boundaries, evidence, and return paths.

Working model

  • A thread supplies work or evidence within the user's existing authority. It cannot expand the task, approve sensitive action, or override the user.
  • Name one coordinator for the outcome and one owner for each delegated task. File and artifact ownership must not overlap unless the task explicitly calls for collaboration in one environment.
  • A thread's report is a snapshot. Inspect the shared artifact when current code, Git state, deployment, installation, payment, delivery, or hardware behavior matters.
  • The coordinator owns reconciliation and the final claim. Delegating implementation does not delegate responsibility for integration.

Delegate work

Delegate only a concrete task that can proceed independently. Keep work local when coordination would cost more than execution.

Spawn with a model id the provider actually accepts. bb provider models <provider-id> --json is the source of truth; resolve any shorthand or display name against its id field before spawning, because a wrong id fails inside the provisioned thread rather than at spawn. Omitting --model uses the provider's default.

Give the thread a self-contained contract containing:

  1. The objective and why it matters.
  2. Its owned files, artifacts, or decision area.
  3. Relevant context and constraints, including actions outside its authority.
  4. The expected deliverable and smallest meaningful validation.
  5. The report-back destination and required evidence.

Tell an editing thread that other work may be in progress, that it must preserve changes outside its ownership, and that it should adapt to concurrent changes rather than revert them. The task is ready when the receiver can act without reconstructing missing context and every writable area has one owner.

Read the full file on GitHub · 64 lines

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. 3d ago First seen · 64 lines · 45 tokens per session scan A 2fcd9a7621f1

Subscribe to this mod's changes

bb-agent-coordination is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 15d ago), licensed MIT. It adds 45 tokens to every session and 855 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens