A guide for designing and changing automated pipelines that build, test, check, and deploy software. It also covers release steps and safe rollback when a deployment goes wrong.

Use it to create or revise CI/CD workflows, quality checks, infrastructure-based environments, release stages, and rollback plans.

It helps make pipeline changes explicit, reviewable, and checked before they reach users. This reduces unclear release processes and unsafe deployments.

mcaf-ci-cd — Skill by managedcode

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 skills/managedcode/mcpgateway/mcaf-ci-cd

Any agent

npx skills add managedcode/MCPGateway --skill mcaf-ci-cd

Clone the repo

git clone --depth 1 https://github.com/managedcode/MCPGateway

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 845 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00048	$0.00845
Opus 5	$0.00024	$0.00423
Sonnet 5	$0.00010	$0.00169
Haiku 4.5	$0.00005	$0.00085

Measured 2d ago against content hash 7cd33d7b7d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcaf-ci-cd 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 2d 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.

.codex/skills/mcaf-ci-cd/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCAF: CI/CD

Trigger On

adding or changing CI workflows
defining release flow or rollback policy
tightening pipeline quality gates
writing or reviewing AI-assisted pipeline YAML

Value

produce a concrete project delta: code, docs, config, tests, CI, or review artifact
reduce ambiguity through explicit planning, verification, and final validation skills
leave reusable project context so future tasks are faster and safer

Do Not Use For

feature-level testing with no pipeline or release impact
general source-control policy without CI/CD changes

Inputs

the current pipeline and release flow
real build, test, analyze, and deploy steps
environment and rollback constraints

Quick Start

Read the nearest AGENTS.md and confirm scope and constraints.
Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
Return the Required Result Format with concrete artifacts and verification evidence.

Workflow

Define the target flow first:
- PR validation
- integration-branch gates
- non-production deployment
- production promotion or release
Keep pipelines reviewable:
- explicit build, test, and analyze steps
- least-privilege secrets and permissions
- rollback or fail-safe strategy
Treat AI-generated YAML as draft content until it is reviewed and validated.
For .NET repositories, make the quality gate explicit:
- formatting ownership
- analyzer ownership
- coverage and report generation
- runner model (VSTest or Microsoft.Testing.Platform)
Pull only the references that match the current delivery problem.

Deliver

CI/CD changes that are explicit, reproducible, and reviewable
release documentation with rollback thinking
pipeline rules aligned with MCAF verification

Validate

every stage has a clear purpose and failure signal
rollback or safe failure is explicit
secrets and permissions are minimized
the pipeline matches the repo’s actual verification model

Read the full file on GitHub · 108 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/ci-cd.md 1.0 KB

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.

2d ago First seen · 108 lines · 48 tokens per session scan A 7cd33d7b7d44

Subscribe to this mod's changes

mcaf-ci-cd is a skill published in the GitHub repository managedcode/MCPGateway (5 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 845 once invoked, about $0.0002 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.

DevOps and cloud Git and workflow Testing ai-extensions csharp dotnet embeddings mcp mcp-gateway

mcaf-ci-cd