Skip to content
Agentmart
Submit a tool

repro-issue

Reproduce a bug and use Argus network mocks to isolate whether it is caused by the frontend or a specific API response.

Skill by Jmsa

IndexedMIT
Write a review

Chalk Labs

Need help deploying repro-issue?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jmsa-repro-issue

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Reproduce a bug and use Argus network mocks to isolate whether it is caused by the frontend or a specific API response. Use when asked to reproduce, isolate, or bisect a bug.

Use cases: frontend, backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/repro-issue

What's inside

Skill name
repro-issue
Description
Reproduce a bug and use Argus network mocks to isolate whether it is caused by the frontend or a specific API response. Use when asked to reproduce, isolate, or bisect a bug.
License
MIT
Instructions
74 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Reproduce and isolate the following issue using Argus: $ARGUMENTS

## Steps

1. **Launch and set up recording**
   ```
   browser_launch
   tab_open { url: "about:blank" }
   console_start { targetId }
   network_start_recording { targetId }
   ```

2. **Add mocks for controlled API responses**
   ```
   network_add_mock {
     targetId,
     urlPattern: "**/api/endpoint",
     responseCode: 200,
     responseBody: '{"key": "value"}',
     responseHeaders: { "content-type": "application/json" }
   }
   ```
   - Use `**` to match any prefix/suffix
   - Mock the API state expected to trigger the bug

3. **Navigate and trigger the issue**
   ```
   tab_navigate { targetId, url: "https://your-site.com/path" }
   page_evaluate { targetId, expression: "document.querySelector('.submit-btn').click()" }
   ```

4. **Capture failure evidence**
   ```
   console_get_logs { targetId, type: "error" }
   network_get_requests { targetId, hasError: true }
   tab_screenshot { targetId, fullPage: true }
   ```

5. **Iterate mocks to find the root cause**
   - Remove the mock: `network_remove_mock { targetId, mockId }`
   - Add a different mock with different data
   - Reload and check if the bug disappears: `page_reload { targetId }`
   - Compare screenshots and logs to pinpoint the problematic state

6. **Verify the fix**
   ```
   network_clear_mocks { targetId }
   network_add_mock { targetId, urlPattern: "**/api/endpoint", responseCode: 200, responseBody: '{"fixed": true}' }
   page_reload { targetId }
   console_get_logs { targetId, type: "error" }   ← should be empty
   tab_screenshot { targetId }                     ← should show fixed state
   ```

7. **Report findings** — include:
   - Which mock configuration reproduced the bug
   - Which change made it disappear
   - Screenshot evidence of both states
   - Recommended fix

## Common Mock Patterns

| Scenario | Mock setup |
|---|---|
| Empty API response | `responseBody: '[]'` or `'{}'` |
| API error | `responseCode: 500, responseBody: '{"error":"Internal Server Error"}'` |
| Auth failure | `responseCode: 401, responseBody: '{"error":"Unauthorized"}'` |

## Tips

- Mock evaluation is first-match — order matters when multiple mocks could match.
- Use `network_list_mocks { targetId }` to verify your mock setup before navigating.
- `console_clear` and `network_clear_requests` before each test run keeps the data clean.

From Jmsa/argus, MIT.

Signals

Stars
0
Forks
0
Open issues
1
Last commit (this folder)
Mar 6, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Jmsa

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get repro-issue running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying repro-issue?

CallGet help
Cite this page

repro-issue skill. Agent Mart. https://agentmart.dev/skills/jmsa-repro-issue (last updated 2026-10-24)