complete-beads

complete-beads is a skill for Claude Code, Codex from FortiumPartners/ensemble. It costs 0 tokens per session (1,944 once invoked), scanned A, original, MIT.

A task-management skill that takes a defined set of development tasks, called beads, from active work to completion or a clearly recorded stopping point. It can plan tasks, assign isolated workers, combine their changes, and report the result.

In plain words
What is it for?
Use it to coordinate multi-step implementation work, run tasks in parallel, integrate the results, and track whether larger work items are complete.
Why use it?
It reduces the risk of tasks being forgotten, left half-done, or merged without a clear completion status.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the ensemble-development plugin — 11 skills, 7 agents shipped together

Good fit Use it to coordinate multi-step implementation work, run tasks in parallel, integrate the results, and track whether larger work items are complete.

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

Made for: Claude Code, Codex.

Or install ensemble-development, the plugin that ships this one along with the rest of its 11 skills, 7 agents.

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 complete-beads

README.md
[![agentmods](https://agentmods.dev/badge/skills/fortiumpartners/ensemble/complete-beads.svg)](https://agentmods.dev/skills/fortiumpartners/ensemble/complete-beads)
Your own site
<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/complete-beads"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/complete-beads.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,944 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 $0.00000 $0.01944
Opus 5 $0.00000 $0.00972
Sonnet 5 $0.00000 $0.00389
Haiku 4.5 $0.00000 $0.00194

Measured 4d ago against content hash bbffc7004e3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

complete-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 4d 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/development/skills/complete-beads/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

complete-beads

Goal-oriented skill that drives every scoped bead to closed or a truthful terminal state. Recovers in-progress work, selects tasks via BV triage/planning, dispatches isolated workers in parallel, integrates serially, and rolls up completed containers. Produces one machine-readable result sentinel.

Replaces the duplicated execution engines in implement-trd-beads and beads-build.


Inputs

Variable Type Description
SCOPE string Project-wide ("") or a root epic bead ID/slug to scope all operations
TRD_PATH string Optional absolute or repo-relative path to a TRD .md file
TRACEABILITY_MAP object Optional map of taskId → {is_test_task, satisfies_req_id, verifies_task_id, ...}
STRATEGY string Implementation strategy: tdd, characterization, bug-fix, refactor, test-after, flexible
BRANCH string Integration branch name (supervisor checkout)
WORKER_SLOTS number Max parallel workers (>= 1; caller resolves from team config or explicit max parallel N)
PR_ACTIONS object[] Ordered PR actions from trd-cli pr-plan (each: {kind, createPr, proposeTitle, branch, parentBranch, appendNextBranch, ...})
RESUME_METADATA object Optional resume state reconstructed from Beads comments ({beadId, childBranch, childWorktree, runId, dispatchBaseSha})

TEAM_MODE is NOT accepted. Slot resolution happens in the calling command before invoking this skill.


Algorithm

Checkpoint Loop

LOOP:
  1. br sync --flush-only
  2. RecoverResume(RESUME_METADATA)   → recovered[], redispatched[]
  3. If recovered or redispatched: re-evaluate → may close or skip beads
  4. br sync --flush-only
  5. RunPlanner()                     → selected[], deferred[]
  6. If selected is empty:
       If deferred.length > 0 → RETURN {status: blocked, reason: deferred[0].deferReason, ...}
       If scoped open beads remain but br ready is empty → RETURN {status:blocked, ...}
       Else → all scoped descendants closed → rollup → RETURN {status:complete, ...}
  7. DispatchBatch(selected)          → results[]
  8. ProcessResults(results)         → may set status=complete|failed
  9. Loop

Read the full file on GitHub · 153 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. 4d ago First seen · 153 lines · 0 tokens per session scan A bbffc7004e3d

Subscribe to this mod's changes

complete-beads is a skill published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,944 tokens. 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.