reproduction-builder

reproduction-builder is a skill for Claude Code from latestaiagents/agent-skills. It costs 52 tokens per session (1,900 once invoked), scanned A, original, MIT.

A guide for creating minimal bug reproductions: small, complete examples that reliably show a problem. It helps document what happened and how others can trigger it.

In plain words
What is it for?
Use it to report bugs, isolate intermittent problems, turn bugs into test cases, and document exact trigger conditions.
Why use it?
It removes unrelated code and unclear steps, making a bug easier to verify and investigate.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the developer-toolkit plugin — 19 skills shipped together

Good fit Use it to report bugs, isolate intermittent problems, turn bugs into test cases, and document exact trigger conditions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/reproduction-builder
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.

Any agent
npx skills add latestaiagents/agent-skills --skill reproduction-builder
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install developer-toolkit, the plugin that ships this one along with the rest of its 19 skills.

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 reproduction-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/reproduction-builder/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/reproduction-builder)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/reproduction-builder"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/reproduction-builder/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 reproduction-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/reproduction-builder"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/reproduction-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00052 $0.01900
Opus 5 $0.00026 $0.00950
Sonnet 5 $0.00010 $0.00380
Haiku 4.5 $0.00005 $0.00190

Measured 10d ago against content hash d78460872c8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reproduction-builder scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# Minimal curl reproduction
plugins/developer-toolkit/skills/debug/reproduction-builder/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reproduction Builder

Create minimal, reliable reproduction cases for bugs.

When to Use

  • Reporting bugs to maintainers
  • Isolating intermittent issues
  • Documenting bugs for your team
  • Creating test cases from bugs
  • Helping others understand an issue

The Minimal Reproduction

A minimal reproduction (repro) is:

  • Minimal - Remove everything not needed to trigger the bug
  • Complete - Contains everything needed to see the bug
  • Verifiable - Others can run it and see the same issue
  • Isolated - No external dependencies if possible

Building a Repro

Step 1: Identify the Symptom

## Bug Symptom

**What I expected:**
When I click "Submit", the form should save and show a success message.

**What actually happened:**
The page refreshes but nothing is saved. No error in UI.

**Error in console (if any):**

TypeError: Cannot read properties of undefined (reading 'id') at saveForm (form.js:45)

Step 2: Find the Trigger

Ask these questions:

  • What action causes the bug?
  • Does it happen every time?
  • What conditions are required?
## Trigger Conditions

**Always happens when:**
- [ ] Form field "email" is empty
- [ ] User is not logged in
- [ ] Data was previously saved

**Sometimes happens when:**
- [ ] Network is slow
- [ ] Multiple tabs open
- [ ] After being idle for a while

**Never happens when:**
- [ ] All fields filled
- [ ] Fresh browser session

Step 3: Isolate Variables

Remove things one at a time until you find the minimum needed.

// Original code with bug
async function saveForm(data: FormData) {
  const validated = await validateForm(data);
  const enriched = await enrichWithUserData(validated);
  const formatted = formatForAPI(enriched);
  const response = await api.post('/forms', formatted);
  await updateLocalCache(response);
  showSuccessMessage();
  analytics.track('form_saved');
  return response;
}

// Isolated - which step fails?
async function saveFormDebug(data: FormData) {
  console.log('1. Input:', data);

  const validated = await validateForm(data);
  console.log('2. Validated:', validated);

  const enriched = await enrichWithUserData(validated);
  console.log('3. Enriched:', enriched);  // Bug here: enriched.user is undefined

  const formatted = formatForAPI(enriched);
  console.log('4. Formatted:', formatted);

  // ... rest
}

Read the full file on GitHub · 345 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 · 345 lines · 52 tokens per session scan A d78460872c8d

Subscribe to this mod's changes

reproduction-builder is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,900 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.