next

next is a command for coding agents from joshsymonds/nix-config. It costs 4 tokens per session (328 once invoked), scanned A, original, MIT.

A command for carrying out a software implementation from a task description using research, planning, implementation, and validation. It includes project-specific quality rules for testing, linting, refactoring, and Go code.

In plain words
What is it for?
Use it for production implementation work, especially tasks involving multiple components, architecture decisions, refactoring, or Go projects.
Why use it?
It provides a repeatable process for turning a request into checked code. The instructions help prevent incomplete refactors, ignored lint warnings, and untested changes.

Command

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.

agentmods
npx agentmods add commands/joshsymonds/nix-config/next
Clone the repo
git clone --depth 1 https://github.com/joshsymonds/nix-config

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 next

README.md
[![agentmods](https://agentmods.dev/badge/commands/joshsymonds/nix-config/next.svg)](https://agentmods.dev/commands/joshsymonds/nix-config/next)
Your own site
<a href="https://agentmods.dev/commands/joshsymonds/nix-config/next"><img src="https://agentmods.dev/badge/commands/joshsymonds/nix-config/next.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00004 $0.00328
Opus 5 $0.00002 $0.00164
Sonnet 5 $0.00001 $0.00066
Haiku 4.5 $0.00000 $0.00033

Measured 5d ago against content hash 4ee685f31acc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

next 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 5d 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.

home-manager/claude-code/commands/next.md · 53 lines

What it actually says

Production Implementation

Implement: $ARGUMENTS

Required Workflow

  1. Research - "Let me research the codebase and create a plan before implementing"
  2. Plan - Present approach for validation
  3. Implement - Build with continuous validation

For complex architecture decisions: "Let me ultrathink about this architecture"

For tasks with independent parts: Spawn multiple agents in parallel

Implementation Standards

Code Evolution

  • Replace old code entirely when refactoring
  • No versioned function names (processV2, handleNew)
  • No compatibility layers or migration code
  • This is a feature branch - implement the final solution directly

Quality Checkpoints

  • Run linters after every 3 file edits
  • Validate each component works before proceeding
  • Run full test suite before completion
  • Fix linter warnings immediately when found

Go-Specific Requirements

  • Use concrete types, not interface{}
  • Simple error handling with standard patterns
  • Channels for synchronization, not time.Sleep()
  • Follow standard project layout (cmd/, internal/, pkg/)
  • Document why decisions were made
  • Add godoc comments for exported symbols

General Requirements

  • Follow existing codebase patterns
  • Use language-appropriate linters at maximum strictness
  • Write tests for business logic
  • Ensure end-to-end functionality

Completion Criteria

  • All linters pass with zero warnings
  • All tests pass (including race detection)
  • Feature works in realistic scenarios
  • No TODOs or temporary code remains
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. 5d ago First seen · 53 lines · 4 tokens per session scan A 4ee685f31acc

Subscribe to this mod's changes

next is a command published in the GitHub repository joshsymonds/nix-config (835 stars, last pushed today), licensed MIT. It adds 4 tokens to every session and 328 once invoked, about $0.0000 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.