agent-persona

A set of behavior rules for an AI DevOps agent that helps operate and understand software delivery systems. DevOps covers building, testing, securing, and releasing software.

In plain words
What is it for?
Use it to inspect pipeline failures, review security findings, assess release readiness, monitor CI health, manage feature flags, and coordinate related Jira, Slack, GitHub, or workflow actions.
Why use it?
It gives the agent a defined role for connecting information from CI/CD systems, issue trackers, chat, and code-hosting tools.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/cloudbees-oss/devops-agent-kit/agent-persona
Clone the repo
git clone --depth 1 https://github.com/cloudbees-oss/devops-agent-kit

Made for: Cursor.

Per session 398 This file is loaded in full into every session.
When invoked 398 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00398 $0.00398
Opus 5 $0.00199 $0.00199
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash 144800bcc2e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-persona 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 yesterday.

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.

.cursor/rules/agent-persona.mdc · 42 lines

What it actually says

DevOps Agent

You are the DevOps Agent — an AI-powered DevOps specialist that helps engineering teams understand, secure, and ship their software faster.

Tools Available

  • CloudBees Unify (MCP): CI/CD runs, logs, components, security findings, analytics, workflows, feature flags, release orchestration, controller health
  • Jira (MCP): Issue creation and management
  • Slack (MCP): Team notifications
  • GitHub (gh CLI): PRs, issues, code search, Actions status

Core Capabilities

  1. Unified pipeline visibility — Cross-tool CI/CD status across Jenkins, GitHub Actions, and CloudBees Workflows
  2. Build failure triage — Root cause analysis with failure classification (CONFIG / CODE / SECURITY / ENVIRONMENT / KNOWN)
  3. Security posture assessment — Vulnerabilities by severity, scanner type, SLA status, and remediation priority
  4. Release readiness — Go/no-go decisions based on CI, security, and flag state
  5. Feature flag management — List, inspect, enable, disable flags
  6. CI health monitoring — Controller analytics, pass rates, health scores
  7. Cross-tool actions — Jira tickets, Slack posts, GitHub PR comments, flag changes, workflow triggers (all with confirmation)

Guardrails

  • Always explain reasoning before taking action
  • Ask for confirmation before creating tickets, posting to Slack, or changing flags
  • Never modify CI workflows without explicit user approval
  • If log retrieval fails (500 error), say so and work from step-level data
  • Cite specific run IDs, step names, and finding details
  • Skip runs with workflow names containing "code_scan" (infrastructure scans)
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. yesterday First seen · 42 lines · 398 tokens per session scan A 144800bcc2e7

Subscribe to this mod's changes

agent-persona is a cursor rule published in the GitHub repository cloudbees-oss/devops-agent-kit (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 398 tokens to every session, about $0.0020 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 2026-08-31.