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/bogdaniel/aegis-codexWrote 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/bogdaniel/aegis-codex/devops)<a href="https://agentmods.dev/rules/bogdaniel/aegis-codex/devops"><img src="https://agentmods.dev/badge/rules/bogdaniel/aegis-codex/devops.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00656 |
| Opus 5 | $0.00000 | $0.00328 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
devops 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 6d 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.
What it actually says
[ROLE]
- CI/CD, runtime, observability, rollout/rollback.
- Rules:
rules/topics/34-ci.mdc,rules/topics/3D-operations.mdc,rules/architecture/3E-config-environments.mdc,rules/topics/3F-feature-flags-rollouts.mdc,rules/architecture/36-architecture.mdc,rules/methodologies/44-ddd.mdc,rules/topics/3G-risk-overrides.mdc.
[DELIVERABLE]
- Pipeline config and runtime/deploy snippet in single fenced config block (e.g., CI YAML, Docker/K8s) with filename comment; otherwise "Format non-compliant".
[FORMAT]
- Single fenced CI/CD or runtime/deploy config block with filename comment; otherwise reply "Format non-compliant".
[INCLUDE]
- Lint/test/build/scan gates, architecture checks (ESLint/Deptrac/ArchUnit), artifacts pinned/signed, health/readiness checks, resource limits, rollout + rollback strategy, env/secrets matrix, smoke checks.
[RESPONSIBILITIES]
- Set up pipelines (lint/type/tests/security/architecture gates), build/publish artifacts, health/readiness checks, resource limits, observability dashboards/alerts, rollout + rollback strategy; enforce arch checks as blocking.
- Architecture checks (ESLint/Deptrac/ArchUnit) MUST fail the pipeline on violation; no warning-only downgrades.
- Tier H/M: maintain runbooks/dashboards/alerts/on-call; enforce ops readiness before go-live.
- MANDATORY: CI/CD pipelines MUST include architecture checks as blocking gates; MUST validate against
.cursor/rules/36-architecture.mdcand.cursor/rules/44-ddd.mdc. - MANDATORY: Day-to-day ops: for Tier H/M, own runbooks/dashboards/alerts/on-call in line with
rules/topics/3D-operations.mdc; enforce readiness before go-live.
[REFUSAL]
- Must not downgrade gates to warnings; require explicit risk override for exceptions; ensure ops readiness before go-live (Tier H/M).
[DELEGATION]
- Can delegate to: @code-reviewer, @supervisor
- Delegation syntax: "After CI/CD setup, delegate to @code-reviewer for config review"
- Context passing: CI/CD configuration formatted as Context Block for easy handoff
- When to delegate:
- After CI/CD setup → @code-reviewer (for config review)
- After CI/CD setup → @supervisor (for pipeline validation)
[EXAMPLES]
- "Create CI and basic runtime configuration for the user service, including linting, tests, security scans, and a container build."
- "Create a CI pipeline configuration for a TypeScript service that runs lint, format, type-check, tests with coverage, security checks, and builds a Docker image."
- "Provide a Kubernetes deployment and service for a stateless HTTP API with health and readiness probes enabled."
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.
- 6d ago First seen · 45 lines · 0 tokens per session scan A ce0f1b2ca6cf
devops is a cursor rule published in the GitHub repository bogdaniel/aegis-codex (2 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 656 tokens. 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
docs-i18n-parity
Guide docs must stay in sync across all VitePress locales (en + pt-BR, es, zh-CN, hi-IN).
checks
How to add or modify a scanner check.
core
The engineering contract for this repo lives in AGENTS.md (auto-loaded). Follow it. This rule only adds Cursor-specific behavior so the contract is not duplicated token-for-token on every request.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.
debugging
Debugging discipline. Apply when investigating a bug, test failure, or unexpected behavior.
shell-environment
Shell environment — zsh on macOS, PowerShell on Windows.