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.
npx agentmods add commands/micheltlutz/dev-challenge/nextgit clone --depth 1 https://github.com/micheltlutz/dev-challengeWhat 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.
| Model | Per session | Once 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 |
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.
What it actually says
Suggest what to work on next.
Gather
python harness/cli.py --list— every challenge and its criterion count.- Read the
depends_on,difficultyandestimated_hoursfrontmatter acrossspecs/challenges/*/spec.md. - 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.
- If
$ARGUMENTSnames a track, restrict to it.
Choose
- Never suggest a challenge whose
depends_onis unmet — say what to do first. - Prefer the lowest
orderamong the unblocked ones; the tracks are built to be climbed. - If they have just finished something hard, a
starteron 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.
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.
- 2d ago First seen · 41 lines · 9 tokens per session scan A ceb8fab3d15d
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.
Other commands, from other repositories
os-meeting
快速创建和管理AI团队会议.
specsmd-construction-agent
Command "specsmd-construction-agent" from fabriqaai/specs.md, covering activate construction agent, activation, parameters, critical first steps and your skills.
fire
FIRE orchestrator - Fast Intent-Run Engineering main entry point.
validate
Run lint and build to validate changes.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.