spark-web: Agent for Claude Code

.cursor/agents/ci-monitor-subagent.md

ci-monitor-subagent is an agent for Claude Code, Cursor from leboncoin/spark-web. It costs 36 tokens per session (5,659 once invoked), scanned A, a copy of ci-monitor-subagent, MIT.

A monitoring agent that checks Nx Cloud CI pipelines, where CI automatically builds and tests code after changes, and reports when the status needs attention. It can also track self-healing progress but does not decide whether changes should be applied or rejected.

In plain words
What is it for?
Use it to poll a branch's CI attempt, detect a new attempt for a commit, track elapsed time, and return a structured status when action is possible.
Why use it?
It removes the need to repeatedly check the CI service by hand and helps the main agent know when a new result is available or waiting has timed out.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

This is leboncoin/spark-web's own configuration. It tells Claude Code and Cursor how to work on spark-web itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spark-web configures →

Reuse

Borrowing it

Nothing to install: this file belongs to leboncoin/spark-web. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/leboncoin/spark-web/main/.cursor/agents/ci-monitor-subagent.md
Clone the repo
git clone --depth 1 https://github.com/leboncoin/spark-web

Made for: Claude Code, Cursor.

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-monitor-subagent

README.md
[![agentmods](https://agentmods.dev/badge/agents/leboncoin/spark-web/ci-monitor-subagent/github.svg)](https://agentmods.dev/agents/leboncoin/spark-web/ci-monitor-subagent)
Your own site
<a href="https://agentmods.dev/agents/leboncoin/spark-web/ci-monitor-subagent"><img src="https://agentmods.dev/badge/agents/leboncoin/spark-web/ci-monitor-subagent/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-monitor-subagent

Your own site · 80×15
<a href="https://agentmods.dev/agents/leboncoin/spark-web/ci-monitor-subagent"><img src="https://agentmods.dev/badge/agents/leboncoin/spark-web/ci-monitor-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,659 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 100% copy Near-identical to another mod 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 $0.00036 $0.05659
Opus 5 $0.00018 $0.02830
Sonnet 5 $0.00007 $0.01132
Haiku 4.5 $0.00004 $0.00566

Measured 7d ago against content hash 5b28159950b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ci-monitor-subagent 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 7d 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.

Origin

This is a copy

100% identical to ci-monitor-subagent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/agents/ci-monitor-subagent.md · 612 lines

How it starts

The opening of the file, as written. The whole thing — 612 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Monitor Subagent

You are a CI monitoring subagent responsible for polling Nx Cloud CI Attempt status and self-healing state. You report status back to the main agent - you do NOT make apply/reject decisions.

Your Responsibilities

  1. Poll CI status using the ci_information MCP tool
  2. Implement exponential backoff between polls
  3. Return structured state when an actionable condition is reached
  4. Track iteration count and elapsed time
  5. Output status updates based on verbosity level

Input Parameters (from Main Agent)

The main agent may provide these optional parameters in the prompt:

Parameter Description
branch Branch to monitor (auto-detected if not provided)
expectedCommitSha Commit SHA that should trigger a new CI Attempt
previousCipeUrl CI Attempt URL before the action (to detect change)
subagentTimeout Polling timeout in minutes (default: 30)
newCipeTimeout Minutes to wait for CI Attempt before returning no_new_cipe (default: 10)
verbosity Output level: minimal, medium, verbose (default: medium)

When expectedCommitSha or previousCipeUrl is provided, you must detect whether a new CI Attempt has spawned.

MCP Tool Reference

ci_information

Input:

{
  "branch": "string (optional, defaults to current git branch)",
  "select": "string (optional, comma-separated field names)",
  "pageToken": "number (optional, 0-based pagination for long strings)"
}

Output:

{
  "cipeStatus": "NOT_STARTED | IN_PROGRESS | SUCCEEDED | FAILED | CANCELED | TIMED_OUT",
  "cipeUrl": "string",
  "branch": "string",
  "commitSha": "string | null",
  "failedTaskIds": "string[]",
  "verifiedTaskIds": "string[]",
  "selfHealingEnabled": "boolean",
  "selfHealingStatus": "NOT_STARTED | IN_PROGRESS | COMPLETED | FAILED | NOT_EXECUTABLE | null",
  "verificationStatus": "NOT_STARTED | IN_PROGRESS | COMPLETED | FAILED | NOT_EXECUTABLE | null",
  "userAction": "NONE | APPLIED | REJECTED | APPLIED_LOCALLY | APPLIED_AUTOMATICALLY | null",
  "failureClassification": "string | null",
  "taskOutputSummary": "string | null",
  "suggestedFixReasoning": "string | null",
  "suggestedFixDescription": "string | null",
  "suggestedFix": "string | null",
  "shortLink": "string | null",
  "couldAutoApplyTasks": "boolean | null",
  "confidence": "number | null",
  "confidenceReasoning": "string | null",
  "hints": "string[]"
}

Read the full file on GitHub · 612 lines

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. 7d ago First seen · 612 lines · 36 tokens per session scan A 5b28159950b2

Subscribe to this mod's changes

ci-monitor-subagent is an agent published in the GitHub repository leboncoin/spark-web (93 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 5,659 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ci-monitor-subagent, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

Actions Manager

GitHub Actions command center -- view workflow runs, read logs, re-run failed jobs, manage workflows, and debug CI failures entirely from the editor. Bypasses the deeply nested, visually-dependent Actions UI that is largely inaccessible to screen readers.

Community-Access/accessibility-agents · 52 tokens

CI Accessibility

CI/CD accessibility agent. Conversational agent for setting up, managing, and troubleshooting accessibility CI pipelines. Supports baseline management (fail only on regressions), SARIF output for GitHub code scanning, PR annotations, and threshold configuration. Works with GitHub Actions, Azure DevOps, GitLab CI…

Community-Access/accessibility-agents · 69 tokens

frontend-engineer

Generates production-grade frontend code (React, Next.js, Vue, Blade+Alpine, vanilla HTML, Astro) with anti-AI-slop discipline. Dispatched by /ux-design, /ux-component, /ux-dashboard, /ux-fix. Owns implementation; the calling command owns orchestration and review.

Laith0003/ux-skill · 69 tokens

devops-engineer

Infrastructure and Operations architect. Specialist in CI/CD, IaC, Global Distribution, and Disaster Recovery.

DDS-Solutions/AI-TadPole-OS · 25 tokens

component-architect

Expert in building design systems with focus on component APIs, reusability patterns, and scalable component architectures. Creates flexible, composable, accessible-by-default components.

NickCrew/Claude-Cortex · 37 tokens

frontend-implementer

Builds production-quality, accessible UI code from a design or brief using the recommended modern stack (React + TypeScript + Tailwind v4 + shadcn/ui + Radix + Motion). Use when the user wants the actual component/page code, not just design direction. Produces clean, typed, accessible, state-complete components.

ca-who-codes/ultimate.UIUX.design.skills · 73 tokens