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/cloudbees-oss/devops-agent-kitWrote 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/rules/cloudbees-oss/devops-agent-kit/tool-usage)<a href="https://agentmods.dev/rules/cloudbees-oss/devops-agent-kit/tool-usage"><img src="https://agentmods.dev/badge/rules/cloudbees-oss/devops-agent-kit/tool-usage/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/rules/cloudbees-oss/devops-agent-kit/tool-usage"><img src="https://agentmods.dev/badge/rules/cloudbees-oss/devops-agent-kit/tool-usage.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 | $0.00798 | $0.00798 |
| Opus 5.5 | $0.00319 | $0.00319 |
| Sonnet 5.5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
tool-usage 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Routing
CloudBees Unify — Component Discovery
| Goal | Tool | Notes |
|---|---|---|
| Find a specific component | components_search |
Search by repo or app name |
| List all components | components_list |
Use when user says "all" or "org" |
CloudBees Unify — CI/CD Analysis
| Goal | Tool | Notes |
|---|---|---|
| Recent runs | runs_list |
Set limit param; filter out code_scan workflows |
| Jobs in a run | automation_jobs_list |
Shows job-level pass/fail |
| Step logs | logs_list |
May 500 — fall back gracefully |
| Workflow YAML | workflow_get_content |
Read to understand step purposes |
| All workflows | workflow_list |
Find CI and release workflows |
| Update workflow | workflow_update_content |
Write — requires user confirmation |
| Trigger workflow | workflow_trigger |
Write — requires user confirmation |
CloudBees Unify — Security
| Goal | Tool | Notes |
|---|---|---|
| Org-wide issues | security_issues_all_get |
All open findings |
| Component branches | branches_list |
Find default branch first |
| Severity breakdown | security_findings_summary_get |
Per component + branch |
| Detailed findings | security_issues_open_get |
Per component + branch |
| Org reports | organizations_suborg_report |
Widgets: s1, s2, s6, s8 (s4/s5 may be empty) |
CloudBees Unify — Controllers
| Goal | Tool | Notes |
|---|---|---|
| Find controllers | controllers_list |
Jenkins instances |
| System info | controllers_data_get(ci2) |
Version, plugins, nodes |
| System health | controllers_data_get(ci3) |
Disk, threads, plugins |
| Runs overview | controllers_data_get(ci4) |
Active, queued, wait times |
| Plugin details | report_drilldown_get(pluginsInfo) |
Plugin health |
CloudBees Unify — Feature Flags
| Goal | Tool | Notes |
|---|---|---|
| Find apps | flags_applications_list |
Flag application discovery |
| List flags | flags_list |
All flags in an app |
| Find flag by name | flags_get_by_name |
Specific flag lookup |
| List environments | flags_environments_list |
Staging, production, etc. |
| Check state | flags_configurations_list |
Current flag state per env |
| Enable/disable | flags_configuration_state_update |
Write — requires confirmation |
| Create flag | flags_add |
Write — requires confirmation |
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.
- 1mo ago First seen · 80 lines · 798 tokens per session scan A 412039f93c86
tool-usage is a cursor rule published in the GitHub repository cloudbees-oss/devops-agent-kit (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 798 tokens to every session, about $0.0032 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .