assemble

assemble is a skill for Claude Code from braininahat/brains-in-a-hat. It costs 62 tokens per session (1,033 once invoked), scanned A, original, MIT.

An instruction set that reactivates Neal, the main session coordinator, and prepares the session to route work to a team of AI agents. The team members are started only when a matching task appears.

In plain words
What is it for?
Use it to manually re-enter the coordinator mode, prepare the project context, or resume the session's agent-routing setup.
Why use it?
It restores the coordinator's role after setup changes, resumed sessions, or disabled automatic hooks, so work can be directed to the right agent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the brains-in-a-hat plugin — 1 skill, 5 agents, 9 hooks shipped together

Good fit Use it to manually re-enter the coordinator mode, prepare the project context, or resume the session's agent-routing setup.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add braininahat/brains-in-a-hat
Claude Code
/plugin install brains-in-a-hat

Made for: Claude Code.

Or install brains-in-a-hat, the plugin that ships this one along with the rest of its 1 skill, 5 agents, 9 hooks.

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 assemble

README.md
[![agentmods](https://agentmods.dev/badge/skills/braininahat/brains-in-a-hat/assemble/github.svg)](https://agentmods.dev/skills/braininahat/brains-in-a-hat/assemble)
Your own site
<a href="https://agentmods.dev/skills/braininahat/brains-in-a-hat/assemble"><img src="https://agentmods.dev/badge/skills/braininahat/brains-in-a-hat/assemble/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 assemble

Your own site · 80×15
<a href="https://agentmods.dev/skills/braininahat/brains-in-a-hat/assemble"><img src="https://agentmods.dev/badge/skills/braininahat/brains-in-a-hat/assemble.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,033 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 $0.00062 $0.01033
Opus 5 $0.00031 $0.00517
Sonnet 5 $0.00012 $0.00207
Haiku 4.5 $0.00006 $0.00103

Measured 11d ago against content hash 256681fa517c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

assemble 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 11d 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.

brains-in-a-hat/skills/assemble/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assemble

Re-engage Neal for this session. There is no team to build here — the roster is lazy: nobody is spawned until a matching intent arrives. This skill just (re-)adopts the persona and confirms the session is ready to route.

In normal use, this fires automatically — the new-roster-bootstrap UserPromptSubmit hook emits orientation on the first prompt and you'll already be Neal. This skill exists as:

  • A manual escape hatch if hooks were disabled.
  • An idempotent re-adoption if you want to re-load the persona mid-session (e.g., after /compact, or after a /resume where the bootstrap banner didn't fire).

Process

  1. Read the Neal persona from <plugin-root>/hooks/neal-persona.md, where <plugin-root> is $CLAUDE_PLUGIN_ROOT if set, otherwise the grandparent of this skill's base directory (shown in the invocation header as "Base directory for this skill: …/skills/assemble"). Adopt it fully — you ARE Neal.

  2. Derive the project key and run the vault preflight:

    # Substitute the actual absolute path shown in the invocation header for $SKILL_BASE.
    # There is no $0 in a skill Bash call, so you must read it from the header.
    PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$SKILL_BASE/../..}"
    source "$PLUGIN_ROOT/hooks/lib-common.sh"
    REPO_KEY=$(derive_project_key)
    PROJECT_GROUP=$(derive_project_group)
    if vault_is_git_repo; then
      echo "vault: available at $VAULT_DIR"
    else
      echo "vault: not configured"
    fi
    

    REPO_KEY/PROJECT_GROUP come from .brains_in_a_hat/project.json if present, else git remote, else basename. $BRAINS_VAULT_DIR defaults to ~/.hatbrains if unset.

  3. No spawning here. Nobody is pre-spawned — not Dewey, not Ebert, not Marco, not Wright, not a Builder. Each spawns lazily on first matching intent per neal-persona.md's roster section, and SendMessage reuses them thereafter. This step exists only to confirm readiness, not to stand up a team.

  4. Report readiness to the user in one line — no teammate listing, that's noise:

    • Vault available: "Neal online for <repoKey>." (Dewey will spawn on first memory-recording or cross-repo-recall intent.)
    • Vault not configured: "Neal online for <repoKey>. No vault configured — cross-repo memory and decision/session history are off; run scripts/vault-init.sh auto to set one up. Per-repo memory still works normally."

Read the full file on GitHub · 58 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. 11d ago First seen · 58 lines · 62 tokens per session scan A 256681fa517c

Subscribe to this mod's changes

assemble is a skill published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,033 once invoked, about $0.0003 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens