dev-orchestrator

dev-orchestrator is a skill for Claude Code, Codex from strigov/superpowers-strigov-ver. It costs 318 tokens per session (20,035 once invoked), scanned B, original, MIT.

A workflow for coordinating multiple coding agents during implementation. The main agent organizes the work while assigned subagents handle code, tests, and reviews.

In plain words
What is it for?
Use it when implementing a requested feature that needs task breakdown, subagent coding, testing, review, and Git coordination.
Why use it?
It keeps production edits out of the coordinating workspace and assigns each task to a focused worker. This provides a defined process for implementation, review, and progress tracking.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also runs codex exec. Also seen: reads .claude/ paths; mentions subagents; names the NotebookEdit tool.

Part of the superpowers-strigov-ver plugin — 16 skills, 1 command shipped together

Good fit Use it when implementing a requested feature that needs task breakdown, subagent coding, testing, review, and Git coordination.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strigov/superpowers-strigov-ver/dev-orchestrator
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 strigov/superpowers-strigov-ver --skill dev-orchestrator
Clone the repo
git clone --depth 1 https://github.com/strigov/superpowers-strigov-ver

Made for: Claude Code, Codex.

Or install superpowers-strigov-ver, the plugin that ships this one along with the rest of its 16 skills, 1 command.

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 dev-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/dev-orchestrator/github.svg)](https://agentmods.dev/skills/strigov/superpowers-strigov-ver/dev-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/strigov/superpowers-strigov-ver/dev-orchestrator"><img src="https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/dev-orchestrator/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.

agentmods 80×15 button for dev-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/strigov/superpowers-strigov-ver/dev-orchestrator"><img src="https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/dev-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 318 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 20,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00318 $0.20035
Opus 5 $0.00159 $0.10018
Sonnet 5 $0.00064 $0.04007
Haiku 4.5 $0.00032 $0.02004

Measured 8d ago against content hash 2ca964829065, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

dev-orchestrator scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- (b) `find <plan-dir> ...` — resume-check / plan-file discovery during phase execution, where `<plan-dir>` is one of `docs/plans/`, `docs/architecture/plans/`, `docs/rfc/`, `.claude/plans/`, `/plans/`. No pipes, no chai
skills/dev-orchestrator/SKILL.md · 640 lines

How it starts

The opening of the file, as written. The whole thing — 640 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Orchestrator

THE HARD RULES (read this first, re-read at every step)

Rule 1 — no writes on main

You are the ORCHESTRATOR on the main thread. You do NOT write production code. You do NOT write tests. You do NOT edit source files. Not one line, regardless of how "trivial" the edit looks or how confident you feel.

Every file change goes through a subagent:

  • Full protocol tasks → Codex implementer, Luna max (./implementer-prompt.md).
  • Trivial single-file edits (<~20 lines, no architectural judgment) → Sonnet quickfix subagent via Agent(subagent_type="general-purpose", model="sonnet", ...). Not you. The subagent.

If you catch yourself about to call Write / Edit / NotebookEdit on a source file: STOP. Dispatch a subagent instead.

The ONLY exceptions — edits you may perform directly on main thread:

  • Plan file (docs/plans/<slug>.md) — frontmatter status flips during auto-commit. Reason: mechanical metadata bookkeeping, not production code.
  • The ledger file (docs/plans/<slug>.ledger.json) — Write / Edit / rm per "## Authorized Change Ledger". Reason: mechanical state-keeping, not production code.
  • Scratch prompt files for --prompt-file dispatches — Write to the scratchpad or workspace, never to source paths. Reason: dispatch plumbing, not production code.
  • Git operations (git add, git commit, git mv — plus creating docs/plans/finished/ — for plan archival, and — for parallel groups — git worktree add/remove, git merge, git branch -d via Bash). Reason: staging/committing/merging/archiving are orchestrator work.

Rule 2 — no research on main

You also do NOT conduct research on the main thread. No reading production code "to understand the task". No Grep/Glob across source to find out how a feature works. No running pytest / linters / build scripts to see what's failing. No reading plan files beyond the YAML frontmatter (single exception: the Step 2.5 pre-flight read — see the list below). "Just a quick look" is still research — STOP.

Read the full file on GitHub · 640 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. 8d ago First seen · 640 lines · 0 tokens per session scan B 2ca964829065

Subscribe to this mod's changes

dev-orchestrator is a skill published in the GitHub repository strigov/superpowers-strigov-ver (4 stars, last pushed 1mo ago), licensed MIT. It adds 318 tokens to every session and 20,035 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens