ensemble-refine-beads

ensemble-refine-beads is a skill for Claude Code, Codex from FortiumPartners/ensemble. It costs 28 tokens per session (1,872 once invoked), scanned A, original, MIT.

A review workflow for improving a Beads task graph before coding begins. Beads is a persistent system that records tasks, hierarchy, priorities, and dependencies.

In plain words
What is it for?
Auditing an epic or project’s Beads structure, identifying proposed repairs, and applying approved graph fixes without implementing or testing the software.
Why use it?
It finds missing tasks, broken dependencies, duplicates, ordering conflicts, and gaps between requirements and acceptance criteria before work starts. Changes require approval.

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 Codex.

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

Good fit Auditing an epic or project’s Beads structure, identifying proposed repairs, and applying approved graph fixes without implementing or testing the software.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fortiumpartners/ensemble/ensemble-refine-beads
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-refine-beads
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-refine-beads

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-refine-beads"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-refine-beads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,872 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 $0.00028 $0.01872
Opus 5 $0.00014 $0.00936
Sonnet 5 $0.00006 $0.00374
Haiku 4.5 $0.00003 $0.00187

Measured 10d ago against content hash e778c3eabc39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ensemble-refine-beads 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-refine-beads/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ensemble Command: /ensemble:refine-beads

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

Refine a Beads dependency graph before execution. The command analyzes a selected epic/release-train subtree by default, or the whole project when --scope project is explicitly supplied. It detects hierarchy gaps, dependency issues, PR-boundary mismatches, missing requirement/AC traceability, duplicate tasks, and priority/order contradictions. Analysis is read-only until the user approves selected fixes.

All Beads updates use br. Graph analysis uses only bv --robot-* flags; never run bare interactive bv. This command uses beads-scaffold-specialist semantics for graph audit/repair work rather than backend-developer. It never executes implementation work, tests, builders, reviewers, branches, commits, or PR creation.

Workflow

Phase 1: Preflight

1. Argument Parsing Parse scope and mode from arguments

  • Parse $ARGUMENTS. If --scope project is present, set SCOPE_MODE=project and warn: "Project scope may affect unrelated epics."
  • Otherwise extract first token as SCOPE_QUERY. It may be an epic ID, release train ID, or slug pattern.
  • If no SCOPE_QUERY and SCOPE_MODE is not project, prepare to list candidate open epics/release trains and ask the user to select one.

2. Tool Availability Check Verify br and detect bv without launching interactive tools

  • Run: which br || { echo "ERROR: br (beads_rust) not installed."; exit 1; }
  • Run: br list --status=open > /dev/null 2>&1 || { echo "ERROR: br not functional — check beads store."; exit 1; }
  • Run: which bv && BV_AVAILABLE=true || { echo "WARNING: bv unavailable; br-only analysis will run."; BV_AVAILABLE=false; }

3. Scope Resolution Resolve exactly one subtree scope or explicit project scope

Read the full file on GitHub · 150 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 · 150 lines · 28 tokens per session scan A e778c3eabc39

Subscribe to this mod's changes

ensemble-refine-beads is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 1,872 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 2026-08-30.