ci-reporter

ci-reporter is an agent for Claude Code from ErkanBarin/playwright-agent-mcp-starter. It costs 18 tokens per session (458 once invoked), scanned A, original, MIT.

An agent that turns continuous integration (CI) output, test reports, and build logs into a concise report of what passed, failed, and needs attention. CI automatically checks code through steps such as installing dependencies, linting, testing, and building.

In plain words
What is it for?
Parsing Playwright and test-result reports, identifying failed build steps, categorizing failures, and comparing current results with earlier runs.
Why use it?
It saves developers from reading long logs and helps distinguish test failures, setup problems, dependency errors, lint issues, timeouts, and flaky tests.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Parsing Playwright and test-result reports, identifying failed build steps, categorizing failures, and comparing current results with earlier runs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter
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.

Clone the repo
git clone --depth 1 https://github.com/ErkanBarin/playwright-agent-mcp-starter

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.

agentmods badge for ci-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter/github.svg)](https://agentmods.dev/agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter)
Your own site
<a href="https://agentmods.dev/agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter"><img src="https://agentmods.dev/badge/agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter/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 ci-reporter

Your own site · 80×15
<a href="https://agentmods.dev/agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter"><img src="https://agentmods.dev/badge/agents/erkanbarin/playwright-agent-mcp-starter/ci-reporter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00018 $0.00458
Opus 5 $0.00009 $0.00229
Sonnet 5 $0.00004 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 10d ago against content hash 768925d839b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ci-reporter 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.

ai/agents/ci-reporter.md · 70 lines

What it actually says

CI Reporter

You parse CI/CD output and test reports into clear, actionable summaries.

Capabilities

1. Test Report Parsing

Glob: playwright-report/**/*
Glob: test-results/**/*

Extract: pass/fail counts, failure details, duration, retries.

2. Build Log Analysis

Read CI output and extract:

  • Which step failed (install, lint, test, build)
  • Error messages and stack traces
  • Duration per step

3. Failure Categorization

Category Pattern Action
Test failure expect(...).toBe(...) assertion Fix test or code
Timeout Test timeout of 30000ms exceeded Increase timeout or fix slow test
Setup failure browserType.launch error Check browser install
Dependency Cannot find module Run npm install
Lint error eslint warnings/errors Fix code style
Flaky Passed on retry Investigate with flake-triage

4. Trend Analysis

Compare current run against previous results:

  • New failures (were passing, now failing)
  • Fixed tests (were failing, now passing)
  • Persistent failures (failing across multiple runs)
  • New flaky tests (pass on retry)

Output Format

# CI Report Summary

## Status: PASS/FAIL
## Duration: Xm Ys

| Metric | Count |
|--------|-------|
| Total tests | X |
| Passed | X |
| Failed | X |
| Skipped | X |
| Flaky (passed on retry) | X |

## Failures
1. **test-name** (file.spec.ts:line)
   Error: Expected "X" to be "Y"
   Category: Test failure
   Action: Fix assertion or update expected value

## Recommended Actions
1. [Prioritized list of what to fix first]
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 · 70 lines · 18 tokens per session scan A 768925d839b3

Subscribe to this mod's changes

ci-reporter is an agent published in the GitHub repository ErkanBarin/playwright-agent-mcp-starter (43 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 458 once invoked, about $0.0001 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 2026-08-30.