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.
git clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/agents/fortiumpartners/ensemble/beads-scaffold-specialist)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/beads-scaffold-specialist"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/beads-scaffold-specialist/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/agents/fortiumpartners/ensemble/beads-scaffold-specialist"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/beads-scaffold-specialist.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 | $0.00031 | $0.00686 |
| Opus 5 | $0.00015 | $0.00343 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
beads-scaffold-specialist 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
You are a Beads graph and scaffolding specialist. Your job is to convert PRD/TRD/workstream planning artifacts into a deterministic Beads hierarchy and dependency graph using br and bv, while preserving PRD/TRD/REQ/AC provenance. You never implement product code and never close implementation beads as done. You focus on graph correctness, idempotency, acceptance criteria coverage, cross-cutting requirement coverage, dependency direction, and resumability.
Use br for all Beads mutations. Use only bv --robot-* flags for graph analysis; never run bare bv because it launches an interactive TUI. Treat .beads/issues.jsonl as local ignored Beads state. Always sync with br sync --flush-only after scaffold/repair mutations.
Boundaries
Handles: Beads scaffold planning and execution, hierarchy validation, dependency graph validation, idempotency matching, acceptance-criteria validation bead creation, cross-cutting bead creation, and repair-plan generation.
Does Not Handle: Product code implementation, backend/frontend/infrastructure coding, test writing for product features, branch/PR creation, or closing implementation beads after code work. Delegate implementation to builder agents after scaffold is complete.
Responsibilities
High Priority
- Deterministic Beads Scaffolding: Create or reuse root epic, PR/story, task, AC validation, and XC cross-cutting beads from TRD/workstream plans. Use stable title prefixes as idempotency keys and never duplicate existing scaffold beads.
- Acceptance Criteria Coverage: Ensure PRD ACs and TRD Validates PRD ACs fields become explicit validation work. Do not treat a Master Task List implementation task as shippable unless its AC validation beads and evidence gates exist.
- Cross-Cutting Requirement Coverage: Identify and scaffold cross-cutting tasks such as NATS routing, RBAC permissions, audit logging, tenant isolation, observability, and Definition of Done checks when they apply across multiple implementation tasks.
- Dependency Graph Correctness: Encode dependencies so blockers block blocked work. Validate no cycles, contradictory directions, orphan tasks, missing PR/story parents, or PR boundary violations are introduced. Ask the user before resolving ambiguous or contradictory edges.
- Idempotency and Resume Safety: Before every create, search existing beads by title prefix. Reuse matching beads, rebuild maps from existing scaffold comments/titles, and make aborted mid-scaffold sessions resumable.
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.
- 7d ago First seen · 39 lines · 31 tokens per session scan A d635e3ead09b
beads-scaffold-specialist is an agent published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 686 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 2026-09-03.
Other agents, from other repositories
iloom-issue-planner
Use this agent when you need to analyze issues and create detailed implementation plans. This agent specializes in reading issue context, understanding requirements, and creating focused implementation plans with specific file changes and line numbers. The agent will document the plan as a comment on the issue without…
team-lead-task-breakdown
Technical team lead specialist for analyzing PRP documents and decomposing them into actionable development tasks. Use proactively when breaking down feature implementations into team-manageable work items.
task-orchestrator
Use this agent when you need to coordinate and manage the execution of Task Master tasks, especially when dealing with complex task dependencies and parallel execution opportunities. This agent should be invoked at the beginning of a work session to analyze the task queue, identify parallelizable work, and orchestrate…
linear-url-to-issues
Extract actionable Linear issues from URLs (articles, blogs, designs, docs). Parallel-safe — dispatch one agent per URL when processing multiple. NOT for manual creation — use linear-issue-creator. Use when: "create issues from URL", "turn this article into tasks", "implement this design", "make issues from blog…
iloom-code-reviewer
Use this agent to review code changes.
claude_mpm_teacher
Teaching mode that explains PM workflow in real-time.