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.
npx agentmods add skills/robisson/build-like-amazon-agent-skills/incremental-implementationnpx skills add robisson/build-like-amazon-agent-skills --skill incremental-implementationgit clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skillsWrote 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/skills/robisson/build-like-amazon-agent-skills/incremental-implementation)<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/incremental-implementation"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/incremental-implementation.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 | $0.00034 | $0.03654 |
| Opus 5 | $0.00017 | $0.01827 |
| Sonnet 5 | $0.00007 | $0.00731 |
| Haiku 4.5 | $0.00003 | $0.00365 |
Grade A, and why
Incremental Implementation 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Incremental implementation means decomposing any feature into the thinnest possible vertical slices—each of which is independently deployable, testable, and rollback-safe. Every slice passes through the full stack (API → logic → storage → observability) rather than building horizontal layers that only work when all layers are combined.
At Amazon, this is not optional. A team that attempts a big-bang release—weeks of uncommitted code merged at once—will face pipeline rejection, delayed launches, and operational incidents. The one-slice-at-a-time principle ensures that at any point in time, main is deployable and the system is in a known-good state.
When to Use
- Starting implementation of any feature approved through design review
- Breaking down a design document into implementation tasks
- Planning sprint work or developer assignments
- Any time a change would touch more than ~200 lines of production code
- When you notice a PR has grown beyond a single logical change
Amazon Context
Amazon deploys million times per year across its services. This velocity is only possible because each deployment is small, reversible, and independent. The culture of "one commit per slice" emerged from painful lessons: large merges cause cascading failures, extended debugging sessions, and blocked pipelines.
Amazon's deployment system enforces bake times between stages. If your deployment contains 15 unrelated changes and one fails, all 15 roll back. This economic reality makes small, focused deployments the only rational strategy.
Feature flags let teams deploy code to production without exposing it to customers. This decouples deployment from release, allowing code to bake safely while business stakeholders decide when to activate.
The Process
1. Slice Identification
Given a design document, decompose the feature into slices using these criteria:
| Criteria | Good Slice | Bad Slice |
|---|---|---|
| Vertical completeness | Touches API → logic → storage → test | Only adds a database table |
| Independent value | Works even if later slices are never built | Requires slice 3 and 5 to function |
| Size | 50-200 lines of production code | 1000+ lines |
| Reviewability | One reviewer can understand in 30 min | Requires 2-hour review meeting |
| Rollback safety | Can be reverted without data migration | Creates irreversible schema 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.
- 5d ago First seen · 233 lines · 34 tokens per session scan A 80b047926efd
Incremental Implementation is a skill published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 3,654 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 2026-08-30.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.