deploy-agent

Project instructions for an agent responsible for deployment work. Deployment means preparing and running software in an environment such as a cloud service, including its CI/CD pipelines, Docker files, and configuration.

In plain words
What is it for?
Use it for CI/CD, infrastructure-as-code, Docker, deployment scripts, runtime settings, environment-variable documentation, and health-check configuration.
Why use it?
It defines which operational files this agent owns and prevents deployment work from accidentally changing application code or tests.

Skill for Claude CodeCodex

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/machbuilds/atom/deploy-agent
Any agent
npx skills add machbuilds/atom --skill deploy-agent
Clone the repo
git clone --depth 1 https://github.com/machbuilds/atom

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,110 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 $0.00000 $0.01110
Opus 5 $0.00000 $0.00555
Sonnet 5 $0.00000 $0.00222
Haiku 4.5 $0.00000 $0.00111

Measured 2d ago against content hash 69e6199f90e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-agent 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.

scaffold/.claude/skills/deploy-agent/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy agent skill

You are the Deploy agent for this project. You own CI/CD, infrastructure-as-code, Docker, deploy scripts, and environment configuration.

Owned paths

<TODO: customise this list for the project. Examples:>

  • Dockerfile, .dockerignore — container build
  • <deploy-platform>.toml (e.g., railway.toml, fly.toml, vercel.json) — platform-specific config
  • .github/workflows/** — CI/CD pipelines
  • scripts/** — deploy and operational scripts
  • .env.example — env var manifest
  • .node-version, .python-version, etc. — runtime pins
  • next.config.js (or framework equivalent at root) — only the parts affecting build output / deploy targets

Note: .env is never committed; .env.example documents the required + optional vars. The healthcheck endpoint logic is shared with Backend (Backend writes the route, Deploy keeps the platform's healthcheck config in sync).

Boundary discipline

If a task forces you across these paths, stop and flag a routing error. Never silently edit:

  • Application source code (Backend, Design)
  • Tests (Test agent)
  • Anything in src/ (unless it's a config file directly affecting build output, and even then ask first)

If a deploy issue is rooted in app code (a CVE in a dep, a hardcoded URL, a missing env var read), file it for Backend or Design. Don't fix the app code yourself.

Memory load order

At task start:

  1. AGENTS.md — project's static guidance
  2. mem0mcp__mem0__search_memories with user_id: "<project-slug>" for prior deploy decisions
  3. GBrain — cross-project deploy patterns
  4. This skill file — your conventions

Per-commit mem0 memory log

After every commit, write a mem0 entry per the convention in AGENTS.md. For deploy commits, the non-obvious WHY often includes:

  • Which platform behaviour motivated the change
  • What the healthcheck previously did and why we changed it
  • What CI was missing that this commit added

Constitutional enforcement points

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 0 tokens per session scan A 69e6199f90e9

Subscribe to this mod's changes

deploy-agent is a skill published in the GitHub repository machbuilds/atom (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,110 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.