boss

boss is a skill for Claude Code from xWael9/ClaudeBoss. It costs 77 tokens per session (905 once invoked), scanned A, original, MIT.

A management mode in which Claude delegates coding work to an opencode agent, reviews the result, and supervises deployment. Claude does not write the implementation itself in this mode.

In plain words
What is it for?
Use it when you want to delegate a defined task, inspect the resulting changes, request up to three rounds of corrections, and oversee deployment after approval.
Why use it?
It keeps the person or reviewing agent focused on task requirements, revisions, approval, and release while another agent handles the code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions OpenCode.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is deploy: ./scripts/deploy.sh.

Part of the claudeboss plugin — 3 skills shipped together

Good fit Use it when you want to delegate a defined task, inspect the resulting changes, request up to three rounds of corrections, and oversee deployment after approval.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/xWael9/ClaudeBoss
agentmods
npx agentmods add skills/xwael9/claudeboss/boss

Made for: Claude Code.

Or install claudeboss, the plugin that ships this one along with the rest of its 3 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 boss

README.md
[![agentmods](https://agentmods.dev/badge/skills/xwael9/claudeboss/boss.svg)](https://agentmods.dev/skills/xwael9/claudeboss/boss)
Your own site
<a href="https://agentmods.dev/skills/xwael9/claudeboss/boss"><img src="https://agentmods.dev/badge/skills/xwael9/claudeboss/boss.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 905 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 $0.00077 $0.00905
Opus 5 $0.00039 $0.00452
Sonnet 5 $0.00015 $0.00181
Haiku 4.5 $0.00008 $0.00090

Measured 7d ago against content hash 9ae2ba62e5f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

boss 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.

skills/boss/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaudeBoss — Boss Mode

You are the boss. The free opencode agent is the worker who writes code and does the heavy lifting. You do not write code yourself in this mode — you delegate, review, request changes, and once the human approves, you supervise deployment.

Drift-prone. Free model catalogs change without notice. Model selection is live via opencode models, never hardcoded.

Prerequisites

claudeboss install must have succeeded at least once on this machine (see the team skill for what it checks). For non-trivial tasks, consider running /claudeboss:plan first to get a reviewed design before delegating implementation here.

Workflow

  1. Classify and delegate. Same task-type classification as team mode. Run:

    claudeboss run <task-type> "<full task spec: what, where, constraints, acceptance criteria>"
    
  2. Review as a manager, not an implementer. Read opencode's output/diff against the acceptance criteria you gave it. Do NOT rewrite it yourself. If it's wrong or incomplete, go back to step 1 with a sharper, more specific instruction naming exactly what's missing or wrong. Cap this at 3 revision rounds. If it still isn't right after 3 rounds, stop delegating and tell the user directly: opencode isn't converging on this task, here's the gap, here's what you'd need (a stronger model, a narrower task, or the user/Claude takes it from here in team mode).

  3. Summarize for the human. Once you approve the output, show the user:

    • What was asked
    • What opencode produced (concrete: files changed, diff summary, or the actual content — not a vague gloss)
    • Your assessment of correctness/risk
    • An explicit question: "Approve to deploy?"

    Do not proceed past this point without an explicit yes. This is a hard gate, not a formality — treat deploys with the same care as any other hard-to-reverse action.

  4. On approval, supervise deployment end-to-end yourself (not opencode) — deployment/ops supervision is the boss's job, not the coding. Drive the actual deploy steps (commit, push, SSH, restart services, whatever the project's real deploy path is), watch for errors at each step, and report status back to the user as it progresses. If a step fails, stop, report what failed and why, and ask before retrying or rolling back — never silently retry a destructive step.

Read the full file on GitHub · 49 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. 7d ago First seen · 49 lines · 77 tokens per session scan A 9ae2ba62e5f9

Subscribe to this mod's changes

boss is a skill published in the GitHub repository xWael9/ClaudeBoss (2 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 905 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

catchup

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

oliver-kriska/claude-elixir-phoenix · 48 tokens

plan

Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.

oliver-kriska/claude-elixir-phoenix · 42 tokens

work

Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.

oliver-kriska/claude-elixir-phoenix · 43 tokens

phx-deps-update

Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).

oliver-kriska/claude-elixir-phoenix · 62 tokens

archive-issue

Retire a closed issue's working artifacts out of specs/ into the GitHub wiki. Use only when the user asks to archive a finished issue, empty out specs/ for a done task, or move an issue's requirements/architecture/tasks/review/QA docs to the wiki.

foyzulkarim/skills · 61 tokens

start-task

Bootstrap a task into a synced feature branch — one shot, zero confirmations. Detects the source from the args: GitHub issue ('#100', 'issue 100', 'gh issue 100', or bare '100'), Jira key ('PROJ-42'), or a local spec file path; ad-hoc conversation otherwise. Fetches the task, derives {type}/{number}/{slug}, syncs the…

foyzulkarim/skills · 125 tokens