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 skills add quay/ai-helpers --skill reproducegit clone --depth 1 https://github.com/quay/ai-helpersWrote 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.
[](https://agentmods.dev/skills/quay/ai-helpers/reproduce)<a href="https://agentmods.dev/skills/quay/ai-helpers/reproduce"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/reproduce/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.
<a href="https://agentmods.dev/skills/quay/ai-helpers/reproduce"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/reproduce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.00992 |
| Opus 5 | $0.00013 | $0.00496 |
| Sonnet 5 | $0.00005 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
reproduce 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 6d 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.
- Bash(curl *) How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reproduce Bug
Confirm the bug exists by reproducing it systematically.
Your Role
Methodically reproduce the bug and document its behavior so that diagnosis and fixing can proceed with confidence.
Process
Step 1: Parse Bug Report
Read the assessment (artifacts/quay-bugfix/reports/assessment.md if it
exists) and extract:
- Bug description and expected vs actual behavior
- Affected components, versions, environment details
- Error messages, stack traces, or relevant logs
- UI vs backend classification
Step 2: Set Up Environment
For backend bugs:
Check what's available and set up accordingly:
# Check for Quay's local dev setup
ls Makefile 2>/dev/null && grep -l 'local-dev' Makefile
# Check for virtual env
ls pyproject.toml requirements.txt 2>/dev/null
Common Quay setup approaches:
make local-dev-up— full local development environment (Docker, DB, Redis)- Virtual environment —
python -m venv .venv && pip install -r requirements.txt - Direct pytest — for unit-level reproduction
For UI bugs:
# Check for frontend dev server
ls web/package.json 2>/dev/null
- Start dev server if needed:
cd web && npm install && npm start - Default app URL:
http://localhost:9000 - Test credentials:
user1/password
Step 3: Attempt Reproduction
Follow the steps from the assessment report. For each attempt, document:
- Exact commands or UI actions performed
- Expected behavior (from bug report)
- Actual behavior (what happened)
- Any error messages or stack traces
Try variations to understand the bug's boundaries:
- Different input values
- Different user roles/permissions
- Different database backends (PostgreSQL vs MySQL)
- Different configurations
- Race conditions (if timing-related)
Step 4: Document Reproduction
Create a minimal set of steps that reliably reproduce the bug.
Step 5: Write Reproduction Report
Save to artifacts/quay-bugfix/reports/reproduction.md:
# Reproduction Report: <TICKET>
## Environment
- Quay version/branch: <branch>
- Setup method: <local-dev-up / venv / docker / pytest>
- Database: <PostgreSQL / MySQL / SQLite>
- Python version: <version>
## Reproduction Steps
1. <exact step>
2. <exact step>
...
## Results
- **Reproduced:** Yes / No / Intermittent
- **Success rate:** Always / Often / Sometimes / Rare
- **Expected:** <what should happen>
- **Actual:** <what does happen>
- **Error output:** <if any>
## Variations Tested
| Variation | Reproduced? | Notes |
|-----------|:-----------:|-------|
| ... | ... | ... |
## Minimal Reproduction
<Shortest path to trigger the bug>
## Notes
<Any observations, workarounds, or additional context>
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.
- 6d ago First seen · 166 lines · 25 tokens per session scan A dc27e74b3888
reproduce is a skill published in the GitHub repository quay/ai-helpers (3 stars, last pushed 23d ago), licensed MIT. It adds 25 tokens to every session and 992 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.