ensemble-beads-build

ensemble-beads-build is a skill for Claude Code, Codex from FortiumPartners/ensemble. It costs 35 tokens per session (9,425 once invoked), scanned A, original, MIT.

A workflow that drives an existing hierarchy of beads—linked epics, stories, and tasks—through implementation, review, and closure.

In plain words
What is it for?
Use it to choose the next ready task, run builder and code-review stages, track quality checks, and close completed work; it can also connect tasks to a Technical Requirements Document.
Why use it?
It selects work based on dependencies and records progress, so a multi-step project can continue across coding-agent sessions.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also installed under .codex/. Also seen: model in frontmatter; mentions subagents; mentions Codex.

Part of the ensemble-codex plugin — 40 skills shipped together

Good fit Use it to choose the next ready task, run builder and code-review stages, track quality checks, and close completed work; it can also connect tasks to a Technical Requirements Document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fortiumpartners/ensemble/ensemble-beads-build
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 FortiumPartners/ensemble --skill ensemble-beads-build
Clone the repo
git clone --depth 1 https://github.com/FortiumPartners/ensemble

Made for: Claude Code, Codex.

Or install ensemble-codex, the plugin that ships this one along with the rest of its 40 skills.

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 ensemble-beads-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-beads-build/github.svg)](https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-beads-build)
Your own site
<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-beads-build"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-beads-build/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 ensemble-beads-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-beads-build"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-beads-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,425 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 $0.00035 $0.09425
Opus 5 $0.00017 $0.04713
Sonnet 5 $0.00007 $0.01885
Haiku 4.5 $0.00003 $0.00942

Measured 10d ago against content hash 42856f8ac5d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ensemble-beads-build 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 10d 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.

packages/codex/.codex/skills/commands/ensemble-beads-build/SKILL.md · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ensemble Command: /ensemble:beads-build

This Codex skill mirrors the Ensemble slash command /ensemble:beads-build. Follow the workflow below, adapt to the current repository, and keep outputs structured.

Drive an existing bead hierarchy (epic -> stories -> tasks) to completion through the full builder -> code-review -> close pipeline. This is the canonical build engine — works for raw beads with no TRD required. implement-trd-beads --execute is effectively a TRD-augmented version of this command.

Uses bv --robot-next for graph-aware task selection (required) or br ready as fallback. Records all state transitions in beads for cross-session resumability. When --trd is provided, enables TRD augmentations: traceability tokens, TRD checkbox sync, and requirement satisfaction report.

Key behaviors:

  • bv --robot-next determines what to run next (fallback: br ready)
  • Quality gates: phase completion triggers test delegation; results recorded as br comments
  • Sync: br sync --flush-only before every bv call
  • Wheel instructions: printed every run with NTM spawn commands for multi-agent flywheel
  • Graceful degradation: bv features skipped if bv unavailable; br required
  • TRD mode: optional --trd flag enables traceability tokens, checkbox sync, requirement report

Workflow

Phase 1: Preflight

1. Argument Parsing Parse epic-id or slug pattern, --trd path, --strategy, and max parallel N

  • Parse $ARGUMENTS: if first token matches pattern beads-NNN or a numeric ID, treat as direct epic bead ID (EPIC_ID_MODE=true); otherwise treat as slug pattern (EPIC_ID_MODE=false)
  • Parse --trd from $ARGUMENTS (optional); if present set TRD_MODE=true and TRD_PATH=; if absent set TRD_MODE=false
  • Parse --strategy from $ARGUMENTS (optional); valid values: tdd, characterization, bug-fix, refactor, test-after, flexible
  • Parse "max parallel N" from $ARGUMENTS (e.g., "max parallel 3") — default MAX_PARALLEL=1 if not present

Read the full file on GitHub · 468 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. 10d ago First seen · 468 lines · 35 tokens per session scan A 42856f8ac5d3

Subscribe to this mod's changes

ensemble-beads-build is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 9,425 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 2026-08-30.