deploy

deploy is a command for Claude Code from robisson/build-like-amazon-agent-skills. It costs 0 tokens per session (596 once invoked), scanned A, original, MIT.

A command for planning and carrying out a safer software release using feature flags, gradual rollout, and pipeline checks. A feature flag is a switch that can turn a feature on or off without redeploying the code.

In plain words
What is it for?
Use it to define flag defaults and kill switches, rollout stages, success and safety metrics, stop conditions, and cleanup after full release.
Why use it?
It limits the impact of a faulty release and defines when to stop, roll back, or remove a feature flag based on observed results.

Command for Claude Code

Part of the build-like-amazon plugin — 28 skills, 14 commands, 10 agents 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 commands/robisson/build-like-amazon-agent-skills/deploy
Clone the repo
git clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skills

Made for: Claude Code.

Or install build-like-amazon, the plugin that ships this one along with the rest of its 28 skills, 14 commands, 10 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/deploy.svg)](https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/deploy)
Your own site
<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/deploy"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/deploy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 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 $0.00596
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 3d ago against content hash dde794b58f83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy 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 3d 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.

.claude/commands/deploy.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy — Progressive Deployment

Path resolution: All skills/, agents/, and patterns/ paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.

You are activating the deploy skill chain: feature-flag-lifecycleprogressive-deploymentpipeline-safety.

What to do

  1. Read skills at skills/feature-flag-lifecycle/, skills/progressive-deployment/, and skills/pipeline-safety/.
  2. Help the user plan and execute a safe deployment strategy.

Step 1: Feature Flag Lifecycle

If the approved design/spec uses feature flags, define the release lifecycle:

  • Flag starts with safe default OFF.
  • OFF behavior preserves existing behavior or graceful fallback.
  • Kill switch behavior is documented and works without deployment.
  • Rollout stages, success metrics, guardrail metrics, and stop conditions are defined.
  • Cleanup task exists for after 100% rollout and stabilization.

If no feature flag is used, state why progressive deployment alone is sufficient.

Step 2: Progressive Deployment

Define the rollout plan:

  • Stage 1 — One-box: Deploy to a single host. Bake for 30+ minutes. Watch error rates.
  • Stage 2 — Regional canary: 5-10% of traffic in one region. Monitor key metrics.
  • Stage 3 — Regional full: Full traffic in one region. Compare against control region.
  • Stage 4 — Global rollout: Expand region by region with bake time between each.

For each stage define:

  • Duration (minimum bake time)
  • Success criteria (metrics that must stay green)
  • Rollback trigger (automatic and manual conditions, including feature flag OFF when applicable)
  • Approval gates (who approves promotion to next stage)

Step 3: Pipeline Safety

Load agents/ops-bar-raiser.md and review the deployment plan through the operations bar raiser lens.

Ensure the deployment pipeline enforces:

  • Automated testing gate: Unit, integration, and contract tests pass.
  • Static analysis gate: No new critical/high findings.
  • Deployment hygiene: Infrastructure-as-code, no manual changes.
  • Rollback capability: One-click rollback to previous known-good version.
  • Alarm integration: Pipeline halts if production alarms fire during bake.
  • Change management: Deployment windows, freeze periods, emergency procedures.

Read the full file on GitHub · 57 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. 3d ago First seen · 57 lines · 0 tokens per session scan A dde794b58f83

Subscribe to this mod's changes

deploy is a command published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 596 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 2026-08-30.