agents: Instructions file for Claude Code

CLAUDE.md

agents CLAUDE.md is an instructions file for Claude Code from navox-labs/agents. It costs 3,869 tokens per session, scanned A, original, MIT.

A repository instruction file for navox-labs/agents. It explains what the repository contains, the rules contributors must follow, and the commands used to work on it.

In plain words
What is it for?
Use it when modifying or reviewing the navox-labs/agents repository, especially its Claude Code subagents, metadata, and README.
Why use it?
It prevents changes that could break the repository's agent-loading conventions, folder structure, prompts, or documentation.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is navox-labs/agents's own configuration. It tells Claude Code how to work on agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to navox-labs/agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/navox-labs/agents/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/navox-labs/agents

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.

agentmods badge for agents CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/navox-labs/agents/claude-md"><img src="https://agentmods.dev/badge/instructions/navox-labs/agents/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,869 This file is loaded in full into every session.
When invoked 3,869 The same file — it is already loaded in full.
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 $0.03869 $0.03869
Opus 5 $0.01935 $0.01935
Sonnet 5 $0.00774 $0.00774
Haiku 4.5 $0.00387 $0.00387

Measured 10d ago against content hash 5919d0a88b4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agents CLAUDE.md 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 10d 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.

CLAUDE.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — navox-labs/agents

This is the build instruction file for the navox-labs/agents repository. Read this entire file before touching any file in this repo.


What this repo is

A collection of Claude Code subagents — 15 specialist AI agents covering the full sprint cycle (Think → Plan → Build → Review → Test → Ship → Reflect) that run entirely inside Claude Code sessions. No platform, no login, no data stored, zero dependencies. Engineers install them globally or per project and hire them via slash commands.

This repo is open source under MIT. It lives at github.com/navox-labs/agents.


Non-negotiable rules

  • Never modify agent prompt content without an explicit instruction to do so — the prompts are the product
  • Never flatten the folder structure — every file has a specific location for a reason
  • Never add dependencies — this repo has zero dependencies by design
  • Never create binary files — everything is markdown
  • Never rename agent files — the filename becomes the slash command name
  • Always validate frontmatter — malformed frontmatter breaks Claude Code agent loading
  • Always keep README.md in sync — if you add/rename an agent, update the README table

Commands

Command What it does
/hire-team Onboard the full 15-agent team, show sprint modes
/agency-run FULL <task> Full sprint: Think → Plan → Build → Review → Test → Ship → Reflect
/agency-run QUICK <task> Quick sprint: Plan → Build → Test → Ship
/agency-run HOTFIX <task> Hotfix sprint: Investigate → Build → Ship
bash scripts/validate.sh Run repo integrity checks (210+ checks across agents, docs, plugins, git)
bash scripts/eval.sh Score each agent 0-10 against quality rubric

Project memory

The team's institutional memory lives in three places:

  • .claude/project-memory.md — shared across all agents, updated after every run
  • .claude/memory/[agent].md — per-agent memory, updated after each agent run
  • .claude/memory/context/ — context snapshots for pause/resume (created by context-manager)

Read the full file on GitHub · 342 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. 10d ago First seen · 342 lines · 3,869 tokens per session scan A 5919d0a88b4b

Subscribe to this mod's changes

agents CLAUDE.md is an instructions file published in the GitHub repository navox-labs/agents (14 stars, last pushed 10d ago), licensed MIT. It adds 3,869 tokens to every session, about $0.0193 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens