What is spec-authoring?

A guide for adding or changing a coding challenge's written specification, acceptance criteria, and matching verification test. Acceptance criteria are named requirements used to decide whether the work is correct.

Use it to create challenges, edit their requirements, define stable criterion IDs, update the harness test, and validate the specification structure.

It keeps the challenge metadata, requirements, API contract, and tests in agreement, so specification changes do not silently diverge from verification.

How micheltlutz/dev-challenge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to micheltlutz/dev-challenge. 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/micheltlutz/dev-challenge/main/.claude/skills/spec-authoring/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/micheltlutz/dev-challenge

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/micheltlutz/dev-challenge/spec-authoring/github.svg)](https://agentmods.dev/skills/micheltlutz/dev-challenge/spec-authoring)

Your own site

<a href="https://agentmods.dev/skills/micheltlutz/dev-challenge/spec-authoring"><img src="https://agentmods.dev/badge/skills/micheltlutz/dev-challenge/spec-authoring/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/micheltlutz/dev-challenge/spec-authoring"><img src="https://agentmods.dev/badge/skills/micheltlutz/dev-challenge/spec-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,491 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.01491
Opus 5.5	$0.00033	$0.00596
Sonnet 5.5	$0.00017	$0.00298
Haiku 4.5	$0.00008	$0.00149

Measured 2mo ago against content hash f709d926013b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-authoring 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 2mo 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/skills/spec-authoring/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring a spec

For contributors extending the lab. The rule that governs everything here: a spec change and its harness test land in the same pull request, or CI rejects it.

Anatomy

specs/challenges/<track>-<nn>-<slug>/
  spec.md          frontmatter + objective + contract + requirements
  acceptance.md    criteria, each with a stable ID

The directory name, the id: in the frontmatter, and the criterion prefix all have to agree.

Frontmatter

Validated against specs/schema/challenge.schema.json.

---
id: backend-05-balance          # must equal the directory name
title: "Balance (amount)"
track: backend                  # backend | web | mobile | fullstack
order: 5                        # unique within the track
difficulty: intermediate        # starter | intermediate | advanced
estimated_hours: 3
depends_on: ["backend-04-statements"]   # must exist, must stay acyclic
endpoints: ["GET /balance/"]            # must exist in specs/openapi.json
acceptance: acceptance.md
verify: "harness/suites/test_balance.py"
tags: ["auth", "business-rules"]
---

Web and mobile additionally require:

figma_node: "13-5855"           # or null
mockups: ["readme_files/images/statement-web.png"]
testids: ["balance-amount", "balance-toggle"]   # non-empty

testids is the contract that makes a UI verifiable without dictating a framework. Choose names that describe the role, not the implementation: balance-toggle, not eye-icon-button.

Set verifiable: false and verify: null when no automated runner can check the challenge — the whole mobile track is in that position, and saying so plainly is better than implying coverage that does not exist.

Writing criteria

### BE05-AC3 — Seeded balance is exact

Given John Doe's token
When GET /balance/
Then `amount` equals 15491.00 within 0.01

IDs are stable and globally unique. <PREFIX><nn>-AC<n>: BE back-end, WEB web, MOB mobile, FS fullstack. Never renumber an existing criterion — append.
One observable behaviour per criterion. If you need "and" in the Then, you probably have two.
Testable from outside. The harness is black-box. "The code is well structured" is not a criterion; "the response contains no password field" is.
Say the number. 15491.00, not "the correct balance".

Read the full file on GitHub · 165 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.

2mo ago First seen · 165 lines · 83 tokens per session scan A f709d926013b

Subscribe to this mod's changes

spec-authoring is a skill published in the GitHub repository micheltlutz/dev-challenge (33 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 1,491 once invoked, about $0.0003 per session on Opus 5.5. 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.

Backend and APIs Mobile Planning Testing challenge development fastapi front-end front-end-challenge

spec-authoring next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spec-authoringmicheltlutz/dev-challenge	Skill	33	5d ago	MIT	A	83	Claude Code
api-contract-testingsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	28	Claude Code
servicenow-api-developmentKnuckles-Team/servicenow-api	Skill	20	yesterday	MIT	A	40	Claude Code, Codex
php-developmentPracticalSwan/agent-skills	Skill	24	18d ago	MIT	A	51	Codex
mongodb-mongoosePracticalSwan/agent-skills	Skill	24	18d ago	MIT	A	43	Codex
sql-developmentPracticalSwan/agent-skills	Skill	24	18d ago	MIT	A	47	Codex
go-servicesalivirgo/Major-AI-Skills	Skill	2	yesterday	MIT	A	38	Claude Code

dev-challenge: Skill for Claude Code