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.
npx skills add sjarmak/coding-agent-workflows --skill focusgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/skills/sjarmak/coding-agent-workflows/focus)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/focus"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/focus"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/focus.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 | $0.00042 | $0.01804 |
| Opus 5.5 | $0.00017 | $0.00722 |
| Sonnet 5.5 | $0.00008 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00180 |
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 16d 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 — 217 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.
parallelselects a dependency-safe wave.--no-closecompletes 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 --jsonsupplies ready tasks.bd show <id> --jsonsupplies acceptance criteria, notes, and dependencies.bd update <id> --claimclaims atomically.bd note <id> "..."records plans, progress, and handoff attestations.bd close <id> --reason "..."closes verified work.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed · +3 lines b968add69add
- 1mo ago Changed · +145 lines · +6 tokens per session 84015bb203cb
- 1mo ago First seen · 69 lines · 36 tokens per session scan A 21d4f773805b
focus is a skill published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 17d ago), licensed MIT. It adds 42 tokens to every session and 1,804 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 2026-08-31.
Other skills, from other repositories
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
exa-search
Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
kimi-webbridge
A way for an AI agent to control the user's real web browser, including pages where the user is already signed in. It can navigate, click, type, read page content, and take screenshots.