Nx is a tool for managing monorepos, which are repositories containing multiple related projects, across TypeScript and other languages. It helps development teams and AI agents run only affected tasks, cache build results, generate code, and coordinate continuous integration. The catalogue add-ons provide agent skills, commands, agents, instructions, and settings for working with Nx.
Borrowing it
Nothing to install: this file belongs to nrwl/nx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nrwl/nx/master/.cursor/agents/ci-watcher.mdgit clone --depth 1 https://github.com/nrwl/nxWrote 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/nrwl/nx/ci-watcher)<a href="https://agentmods.dev/agents/nrwl/nx/ci-watcher"><img src="https://agentmods.dev/badge/agents/nrwl/nx/ci-watcher/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/nrwl/nx/ci-watcher"><img src="https://agentmods.dev/badge/agents/nrwl/nx/ci-watcher.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 | $0.00037 | $0.04299 |
| Opus 5.5 | $0.00015 | $0.01720 |
| Sonnet 5.5 | $0.00007 | $0.00860 |
| Haiku 4.5 | $0.00004 | $0.00430 |
Grade A, and why
ci-watcher 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ci-watcher — 98% identical, 57 lines differ
How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Watcher 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
- Poll CI status using the
ci_informationMCP tool - Implement exponential backoff between polls
- Return structured state when an actionable condition is reached
- Track iteration count and elapsed time
- 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: 60) |
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"
}
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.
- 10d ago Changed · -3 lines 92bb5e4b6eec
- 1mo ago First seen · 481 lines · 37 tokens per session scan A 6db6fbe385e1
ci-watcher is an agent published in the GitHub repository nrwl/nx (29,421 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 4,299 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
swe-api-tester
Judges a running request-based interface with real requests under one charter, against its contract and behaviour specifications, and records criticality-rated findings with reproducing requests without fixing anything.
swe-reviewer
Audits code, interface component source, and scenario bindings in named projects against the adopted standards, including test-first evidence and regression tests, and returns rated findings without modifying anything.
swe-web-tester
Judges a running web interface in a real browser under one charter, against its specification, its approved design, or frozen exploratory charters, and records criticality-rated findings with reproduction steps without fixing anything.
docs-link-checker
Validates internal and external documentation links. Always uses docs/metadata/external-links-status.yaml as its sole cache, prunes it, and updates lastFullScan on every invocation. Use for dead links, URL reachability, internal references, or link-health audits.
harness-checker
Audits a repository's harness bindings for internal parity with their canonical sources and for drift from each harness's current documented conventions, and returns rated findings without editing.
plan-checker
Audits a complete plan draft against the plan specification and returns criticality-rated findings to the plan quality gate, without modifying anything it audits.