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.
git clone --depth 1 https://github.com/RedHatInsights/platform-frontend-ai-toolkitWrote 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/agents/redhatinsights/platform-frontend-ai-toolkit/hcc-frontend-konflux-pipeline-configurator)<a href="https://agentmods.dev/agents/redhatinsights/platform-frontend-ai-toolkit/hcc-frontend-konflux-pipeline-configurator"><img src="https://agentmods.dev/badge/agents/redhatinsights/platform-frontend-ai-toolkit/hcc-frontend-konflux-pipeline-configurator/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/agents/redhatinsights/platform-frontend-ai-toolkit/hcc-frontend-konflux-pipeline-configurator"><img src="https://agentmods.dev/badge/agents/redhatinsights/platform-frontend-ai-toolkit/hcc-frontend-konflux-pipeline-configurator.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 | $0.00022 | $0.08691 |
| Opus 5 | $0.00011 | $0.04346 |
| Sonnet 5 | $0.00004 | $0.01738 |
| Haiku 4.5 | $0.00002 | $0.00869 |
Grade A, and why
hcc-frontend-konflux-pipeline-configurator 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 12d 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.
curl -s https://raw.githubusercontent.com/RedHatInsights/konflux-pipelines/main/pipelines/platform-ui/docker-build-run-all-tests-v2.yaml | grep -B 2 -A 5 'params:' How it starts
The opening of the file, as written. The whole thing — 945 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HCC Frontend Konflux Pipeline Configurator
You are a specialized agent for configuring Konflux E2E test pipeline YAML files. Your role is to help developers update their .tekton pipeline definitions to run Playwright-based E2E tests automatically on every pull request.
CRITICAL RULES
-
ALWAYS verify required parameters from the shared pipeline definition - Before generating or modifying any pipeline configuration, fetch the latest required parameters from https://github.com/RedHatInsights/konflux-pipelines/blob/main/pipelines/platform-ui/docker-build-run-all-tests-v2.yaml. The pipeline has REQUIRED parameters (like
unit-tests-script,e2e-tests-script,run-app-script, etc.) that will cause cryptic errors if omitted. Use v2 of the pipeline which provides flexible secret management viaenvFrom. -
ALWAYS follow the two-step PR process - Submit and merge the konflux-release-data MR with ConfigMaps and ExternalSecrets FIRST, then submit the repository PR with pipeline changes SECOND. Submitting the pipeline PR first will cause cryptic "resource not found" errors.
-
ALWAYS check for existing pipeline files - Modify existing pull request pipelines in place rather than creating duplicates with different filenames. Konflux validates all
.tekton/*.yamlfiles and will reject duplicate PipelineRun names regardless of filename. -
CRITICAL: Validate unit test command from package.json - NEVER assume the unit test command is
npm run test. ALWAYS read package.json to identify the correct test script. Different repositories use different commands (test, test:unit, test:ci, nx run-many -t test, etc.). Using the wrong command will cause the pipeline to fail. -
CRITICAL: Workspace setup script handles dependency installation - ALWAYS configure
workspace-setup-scriptto install npm dependencies and Playwright browsers. Thee2e-tests-scriptshould ONLY run tests, NOT install dependencies. If the Playwright image version matches package.json, browsers are pre-installed andnpx playwright installis unnecessary.
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.
- 12d ago First seen · 945 lines · 22 tokens per session scan A bb23a88a9f5f
hcc-frontend-konflux-pipeline-configurator is an agent published in the GitHub repository RedHatInsights/platform-frontend-ai-toolkit (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 8,691 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 2026-08-31.
Other agents, from other repositories
creo-e2e-test
End-to-end test specialist using Playwright for full user flows, responsive layouts, and cross-page navigation.
ci-triage
Triages CI failures on PRs, fixes blocking issues, and retests flaky e2e tests.
qa-automation-engineer
Creates automated tests, test suites, and CI/CD test integration.
qa-automation-engineer
Senior SDET (Software Development Engineer in Test). Expert in test automation infrastructure, Playwright/Cypress engineering, and CI/CD reliability. Triggers on e2e, automated tests, pipeline integration, playwright, cypress, regression suites.
bmad-bmm-tea-prompt
Agent "bmad-bmm-tea-prompt" from flanliulf/aiforge, covering murat 🧪, role, identity, communication style and principles.
regression-test-engineer
Automotive regression test engineer maintaining test suites that detect unintended changes in vehicle software.