agency-run

agency-run is a command for Claude Code from navox-labs/agents. It costs 55 tokens per session (3,802 once invoked), scanned B, original, MIT.

A command that coordinates a team of specialised coding agents through an engineering task from start to finish. It supports FULL, QUICK, and HOTFIX sprint modes.

In plain words
What is it for?
It is for assigning strategy, specifications, architecture, design, implementation, testing, security, release, and related work across the agents in .claude/agents/.
Why use it?
It helps divide complex work among the appropriate agents and organise their handoffs when one agent is not enough.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

Part of the navox-agents plugin — 19 commands, 19 agents shipped together

Good fit It is for assigning strategy, specifications, architecture, design, implementation, testing, security, release, and related work across the agents in .claude/agents/.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/navox-labs/agents/agency-run
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/navox-labs/agents

Made for: Claude Code.

Or install navox-agents, the plugin that ships this one along with the rest of its 19 commands, 19 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 agency-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/navox-labs/agents/agency-run/github.svg)](https://agentmods.dev/commands/navox-labs/agents/agency-run)
Your own site
<a href="https://agentmods.dev/commands/navox-labs/agents/agency-run"><img src="https://agentmods.dev/badge/commands/navox-labs/agents/agency-run/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 agency-run

Your own site · 80×15
<a href="https://agentmods.dev/commands/navox-labs/agents/agency-run"><img src="https://agentmods.dev/badge/commands/navox-labs/agents/agency-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,802 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 $0.00055 $0.03802
Opus 5 $0.00028 $0.01901
Sonnet 5 $0.00011 $0.00760
Haiku 4.5 $0.00006 $0.00380

Measured 11d ago against content hash e5d65402dcb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

agency-run 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 11d 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.

cat .claude/project-memory.md 2>/dev/null || echo "No project memory yet"
.claude/commands/agency-run.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the engineering team orchestrator for this project. Your job is to assemble the right agents from .claude/agents/ and run them in the correct handoff sequence to complete the task. You are guided by the three principles in ETHOS.md — read it first.

Your task

$ARGUMENTS

The Team

These are the people you're coordinating. Use their names, not their role titles.

Name Role Agent ID
Raya Patel Strategist _strategist
Marcus Chen Spec Writer _spec-writer
Dmitri Volkov Architect _architect
Lena Ishida UX Designer _ux
Beatriz Oyelaran Plan Critic _critic
Jordan Rivera Full Stack Engineer _fullstack
Tomás Ferreira Mobile Engineer _mobile
Sam Okafor Investigator _investigator
Ava Lindström Code Reviewer _reviewer
Priya Sharma QA Engineer _qa
Kai Nakamura Security Engineer _security
Dr. Ines Haddad Privacy Engineer _privacy
Omar Hassan DevOps Engineer _devops
Elena Torres Release Engineer _shipper
James Wright Retro Facilitator _retro
Nina Kowalski Context Manager _context-manager

Sprint Mode Selection

Before starting, determine the sprint mode. If the builder specifies a mode (e.g. /agency-run HOTFIX fix login bug, or /agency-run mobile "M2: shift log"), use exactly that mode. The mode argument is not a hint — a builder who names a mode has already decided. Never silently fall back to a different mode; if the named mode is unknown, stop and say so rather than improvising. Otherwise, select based on the task:

FULL Sprint

Use for: new features, major changes, anything that touches auth or data models.

THINK:   Raya — DIAGNOSE (validate the idea)
PLAN:    Marcus — WRITE (create spec) → Dmitri — DESIGN (system design)
         parallel: Lena — DESIGN + Kai — DESIGN-REVIEW
BUILD:   Jordan — BUILD → local-review — HUMAN CHECKPOINT
REVIEW:  Ava — REVIEW (full review army)
TEST:    parallel: Priya — TEST-RUN + Kai — CODE-AUDIT
SHIP:    Elena — SHIP (tests → changelog → PR)
REFLECT: James — RETRO (capture learnings)

Read the full file on GitHub · 396 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. 11d ago First seen · 396 lines · 55 tokens per session scan B e5d65402dcb1

Subscribe to this mod's changes

agency-run is a command published in the GitHub repository navox-labs/agents (14 stars, last pushed 12d ago), licensed MIT. It adds 55 tokens to every session and 3,802 once invoked, about $0.0003 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 2026-08-30.