next

A command that recommends the next development challenge based on dependencies, difficulty, estimated time, and completed work. A dependency is an earlier exercise that must be finished first.

In plain words
What is it for?
Use it to select an unblocked challenge, understand what it builds on and unlocks, and compare it with one alternative.
Why use it?
It prevents choosing an exercise whose prerequisites are incomplete and helps keep progress aligned with the available learning tracks.

Command for Claude Code

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/micheltlutz/dev-challenge/next
Clone the repo
git clone --depth 1 https://github.com/micheltlutz/dev-challenge

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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 $0.00009 $0.00381
Opus 5 $0.00005 $0.00191
Sonnet 5 $0.00002 $0.00076
Haiku 4.5 $0.00001 $0.00038

Measured 2d ago against content hash ceb8fab3d15d, 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 2d 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/commands/next.md · 41 lines

What it actually says

Suggest what to work on next.

Gather

  1. python harness/cli.py --list — every challenge and its criterion count.
  2. Read the depends_on, difficulty and estimated_hours frontmatter across specs/challenges/*/spec.md.
  3. If you know where their app runs, run the harness to see what already passes. If not, ask what they have finished rather than assuming.
  4. If $ARGUMENTS names a track, restrict to it.

Choose

  • Never suggest a challenge whose depends_on is unmet — say what to do first.
  • Prefer the lowest order among the unblocked ones; the tracks are built to be climbed.
  • If they have just finished something hard, a starter on another track is a reasonable change of pace. Offer it, do not insist.
  • Someone who has finished a backend and a web challenge on the same feature is ready for the fullstack track — that is where SDD actually pays off, because neither side of the contract is given to them.

Say

  • The recommendation, and why it follows from what they have done.
  • What it builds on, and what it unlocks.
  • Difficulty and rough hours.
  • One alternative, if there is a sensible one.

Keep it to a few lines. Then offer to run /challenge <id>.

If everything in a track is done, say so and point at another track or at ROADMAP.md — contributing a challenge is the natural next step for someone who has finished one.

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. 2d ago First seen · 41 lines · 9 tokens per session scan A ceb8fab3d15d

Subscribe to this mod's changes

next is a command published in the GitHub repository micheltlutz/dev-challenge (32 stars, last pushed 15d ago), licensed MIT. It adds 9 tokens to every session and 381 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.