repro-first

repro-first is a skill for Claude Code, Codex from chipi/agentic-ai-homelab. It costs 68 tokens per session (373 once invoked), scanned A, original, MIT.

A bug-fixing method that requires a failing test or other reproducible case before changing the code. The test remains afterward to catch the same bug again.

In plain words
What is it for?
Use it for reported bugs, production incidents, or investigations where something is broken. It covers unit tests, integration cases, fixtures, and test-matrix entries.
Why use it?
It prevents guesses about the cause and makes sure the fix addresses a real, demonstrated failure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for reported bugs, production incidents, or investigations where something is broken. It covers unit tests, integration cases, fixtures, and test-matrix entries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chipi/agentic-ai-homelab/repro-first
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 chipi/agentic-ai-homelab --skill repro-first
Clone the repo
git clone --depth 1 https://github.com/chipi/agentic-ai-homelab

Made for: Claude Code, Codex.

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 repro-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/repro-first/github.svg)](https://agentmods.dev/skills/chipi/agentic-ai-homelab/repro-first)
Your own site
<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/repro-first"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/repro-first/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 repro-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/repro-first"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/repro-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 373 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.
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 $0.00068 $0.00373
Opus 5 $0.00034 $0.00187
Sonnet 5 $0.00014 $0.00075
Haiku 4.5 $0.00007 $0.00037

Measured 10d ago against content hash aefb15e867a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

repro-first 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 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.

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.

workstation/claude/skills/repro-first/SKILL.md · 30 lines

What it actually says

repro-first

A real bug gets a failing test that reproduces it before the fix lands. The test is the regression guard for next time. No fix without a repro.

Steps

  1. Reproduce locally first. Pull evidence for THIS specific failure — the actual error, log, stack trace, or input. Don't theorize a root cause from "usually it's X"; get the real signal for this run.
  2. Write the failing test at the right layer — unit test, integration case, fixture, or a matrix row — that fails because of the bug. Run it; confirm it fails for the expected reason (red for the right cause, not a typo).
  3. Fix the code.
  4. Confirm green + no collateral. The new test passes, and the surrounding suite still passes — run the gate that covers the change, not the whole world.
  5. Keep the test. It ships with the fix in the same change. Don't delete it, don't mark it skip — it's the guard for the next regression.

Non-negotiables this enforces

  • Real bug → repro before fix (rule #34): the failing test lands with the fix.
  • Never invent root causes (rule #5): evidence for this run before a theory.
  • Reproduce locally before pushing (rule #11).
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 · 30 lines · 68 tokens per session scan A aefb15e867a5

Subscribe to this mod's changes

repro-first is a skill published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 373 once invoked, about $0.0003 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 2026-08-31.