deploy-guide

deploy-guide is a skill for Claude Code, Codex from pitimon/8-habit-ai-dev. It costs 38 tokens per session (2,170 once invoked), scanned A, original, MIT.

A guided process for deploying software to staging or production, with checks for the existing deployment setup and a rollback plan. Staging is a test environment used before production, where users run the live system.

In plain words
What is it for?
Use it to inspect deployment scripts and CI/CD settings, classify changes, plan staged rollouts, verify health, and prepare recovery steps.
Why use it?
It helps prevent risky direct production releases and makes deployment steps fit the kind of change being made.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

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/pitimon/8-habit-ai-dev/deploy-guide
Any agent
npx skills add pitimon/8-habit-ai-dev --skill deploy-guide
Clone the repo
git clone --depth 1 https://github.com/pitimon/8-habit-ai-dev

Made for: Claude Code, Codex.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

Wrote 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.

agentmods badge for deploy-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/deploy-guide.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/deploy-guide)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/deploy-guide"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/deploy-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,170 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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.02170
Opus 5 $0.00019 $0.01085
Sonnet 5 $0.00008 $0.00434
Haiku 4.5 $0.00004 $0.00217

Measured 4d ago against content hash 1642d20870b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-guide 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 4d 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.

plugin/skills/deploy-guide/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 6: Deploy (ปล่อยของ)

Habit: H1 — Be Proactive | Anti-pattern: Deploying directly to production without staging

Process

  1. Check existing deploy infrastructure: Read deploy scripts, CI/CD configs, docker-compose files, Makefiles — understand what's already automated.

  2. Classify the deploy type before planning rollout:

    • image build — artifact/image changes; deploy the new artifact through staging first.
    • mounted config/template — runtime reads a file mounted from host/volume; plan config render, sync, service reload/restart, and verification.
    • Swarm configdocker config/secret object changes; plan config object replacement plus service update.
    • full stack — compose/stack topology changes; plan broader blast radius and rollback.
    • source-of-truth drift — repo/template says one thing but live runtime reads another; reconcile before deploy.
    • force-update only — no artifact/config change, but scheduler needs a controlled restart; still needs health/rollback checks.
    • production canary / capacity change — cloud/provider-managed infrastructure change where the operator can pick a canary but the provider may mutate a different resource; plan reconciliation gates.
    • no deploy — truly non-runtime work.
  3. Staging first (ALWAYS when deploy type has runtime impact):

    Step 1: Build artifacts (images, bundles)
    Step 2: Deploy to staging
    Step 3: QA on staging (health check, feature verify, smoke test)
    Step 4: Deploy to production
    Step 5: QA on production (verify version, health, features)
    
  4. Pre-deploy checklist:

    • All tests pass
    • Code review completed
    • Version bumped (if applicable)
    • Environment variables validated
    • Rollback plan documented
  5. Plugin release decision gate (for this repo and other installed plugins): classify the PR before bumping version files.

    • Release now — the PR changes installed-user surfaces: skills/, guides/, hooks/, package manifests, AGENTS.md, llms.txt, generated catalogs, install/update docs, runtime-boundary docs, or root context files that plugin users should receive.
    • Bundle later — the PR is consumer-facing but not urgent; merge only without a version bump, record the bundle target, and leave release links untouched.
    • No release — the PR is contributor-only: tests, CI, ADRs, internal docs, or validator maintenance that does not change installed-user behavior or package contents.

Read the full file on GitHub · 142 lines

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. 4d ago First seen · 142 lines · 38 tokens per session scan A 1642d20870b3

Subscribe to this mod's changes

deploy-guide is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,170 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.

Related

Other skills, from other repositories

next

Use at the start of a work session, or any time the question is "what should I pick up now" across the whole project. Triggers — "/engineer.next", "what's next", "what should I work on", "what should I do next", "where do I pick up".

swingerman/engineer · 64 tokens

crap-analyzer

Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …

swingerman/engineer · 109 tokens

session-summary

Use at the end of a work session on a DAE feature, so the next session picks up cleanly. Triggers — "/engineer.session-summary", "wrap up the session", "write the session log", "I'm stopping for the day".

swingerman/engineer · 54 tokens

pulumi-best-practices

Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow.…

pulumi/agent-skills · 92 tokens

pulumi-cdk-to-pulumi

Load this skill when a user wants to migrate, convert, port, translate, or move an AWS CDK application (including CDK stacks, constructs, or CloudFormation-synthesized templates) to Pulumi. Phrases such as "convert CDK to Pulumi", "migrate CDK app", "port CDK stacks", "replace CDK with Pulumi", "stop using CDK". Do…

pulumi/agent-skills · 118 tokens

onboard

Use to bring a project into the DAE methodology, or to check an onboarded project for gaps. Triggers — "/engineer.onboard", "onboard this project", "set up DAE here", "adopt the methodology", or when a DAE skill fails because no manifest exists.

swingerman/engineer · 64 tokens