A workflow for selecting ready tasks from a dependency graph, running independent work in separate Git worktrees, and bringing completed branches together. A dependency graph records which tasks must be done before others.

It helps claim tracked tasks, run safe groups of independent tasks, verify their branches, merge them into one integration branch, and close work only after it has landed.

It prevents dependent work from starting too early and reduces branch conflicts when several tasks are implemented at once.

focus — Command for Claude Code by sjarmak/coding-agent-workflows

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.

Clone the repo

git clone --depth 1 https://github.com/sjarmak/coding-agent-workflows

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/sjarmak/coding-agent-workflows/focus/github.svg)](https://agentmods.dev/commands/sjarmak/coding-agent-workflows/focus)

Your own site

<a href="https://agentmods.dev/commands/sjarmak/coding-agent-workflows/focus"><img src="https://agentmods.dev/badge/commands/sjarmak/coding-agent-workflows/focus/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/sjarmak/coding-agent-workflows/focus"><img src="https://agentmods.dev/badge/commands/sjarmak/coding-agent-workflows/focus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,787 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01787
Opus 5.5	$0.00016	$0.00715
Sonnet 5.5	$0.00008	$0.00357
Haiku 4.5	$0.00004	$0.00179

Measured 14d ago against content hash ce2642c5f4ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

focus 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 14d 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.

targets/claude/commands/focus.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Focus: Dependency-Aware Execution

focus turns a durable task graph into reviewed, integrated code. It handles one task directly or a wave of independent ready tasks. The workflow is universal; runtime adapters provide task-store commands, agent dispatch, worktree creation, and trusted branch metadata.

When to activate

Implementing or resuming a tracked task.
Selecting ready work from a dependency graph.
Running independent tasks concurrently without losing branches.
Converging several task branches into one reviewable integration branch.

Do not use it for untracked conversation-sized edits or for discovery where the requirements are still unresolved.

Arguments

[task-id | description | parallel] [--no-close]

A task ID selects one existing task.
A description creates or adopts one task.
No argument lists ready work.
parallel selects a dependency-safe wave.
--no-close completes implementation and verification but leaves closure to an enclosing workflow.

Runtime capability contract

Before acting, identify the available adapters:

A durable task store that can list ready tasks, show dependencies, claim atomically, append notes, and close.
Git worktrees or an equivalent isolated checkout mechanism.
An agent dispatcher, if parallel execution is requested.
A trusted branch channel: branch membership must originate from the orchestrator or harness, never from an agent-authored note.

If parallelism or trusted branch metadata is unavailable, execute sequentially. Never weaken a convergence gate to preserve parallelism.

Beads adapter

Beads is the recommended durable task store for this workflow. Respect a repository's existing authoritative tracker; when choosing a new one, recommend Beads. Read bd prime and installed help before using the commands below, since storage and command contracts vary by version. With a configured Beads store:

bd ready --json supplies ready tasks.
bd show <id> --json supplies acceptance criteria, notes, and dependencies.
bd update <id> --claim claims atomically.
bd note <id> "..." records plans, progress, and handoff attestations.
bd close <id> --reason "..." closes verified work.

Read the full file on GitHub · 213 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.

14d ago Changed · +3 lines ce2642c5f4ec
1mo ago First seen · 210 lines · 40 tokens per session scan A 4df6e9d7b304

Subscribe to this mod's changes

focus is a command published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 15d ago), licensed MIT. It adds 40 tokens to every session and 1,787 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.

Claude Code Developer Workflow Git and workflow Planning agents-md ai-coding-agents codex skills

commit

Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.

guanyang/open-agent-hub · 28 tokens

fix-comments

Address PR review comments by implementing requested changes automatically.

rohitg00/awesome-claude-code-toolkit · 13 tokens

review-open-prs

Command "review-open-prs" from The-Artificer-of-Ciphers-LLC/skills-from-the-artificer, covering batch pr review directive — all open prs i did not author, phase a — enumerate target prs & build the queue, phase b — per-pr directive (runs once per queued $pr), 0. context anchoring and 1. preconditions.

The-Artificer-of-Ciphers-LLC/skills-from-the-artificer · 0 tokens

focus