What is sample-agent-assisted-sdlc CLAUDE.md?

A project instruction file describing an agent-assisted software development project built on Amazon Bedrock AgentCore. It documents commands, the cloud architecture, source directories, configuration, and development conventions.

Use it as repository guidance when installing dependencies, testing, synthesising or deploying infrastructure, and locating stacks, assistants, and developer tools.

It gives coding agents project-specific context so they can use the right commands, understand the system's components, and follow repository conventions.

How aws-samples/sample-agent-assisted-sdlc configures Claude Code

About the project

Agent-Assisted SDLC is a sample software development pipeline in which an AI coding assistant reads an issue, changes a codebase, and opens a pull request through Amazon Bedrock AgentCore. Developers use it to automate work from an issue to a proposed code change, with a shared orchestration process and repository-specific guidance. The catalogue entries provide the skills, agents, plugin, hook, and instruction used by this workflow.

aws-samples/sample-agent-assisted-sdlc · 47 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to aws-samples/sample-agent-assisted-sdlc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/aws-samples/sample-agent-assisted-sdlc/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/aws-samples/sample-agent-assisted-sdlc

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/aws-samples/sample-agent-assisted-sdlc/claude-md/github.svg)](https://agentmods.dev/instructions/aws-samples/sample-agent-assisted-sdlc/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/aws-samples/sample-agent-assisted-sdlc/claude-md"><img src="https://agentmods.dev/badge/instructions/aws-samples/sample-agent-assisted-sdlc/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/aws-samples/sample-agent-assisted-sdlc/claude-md"><img src="https://agentmods.dev/badge/instructions/aws-samples/sample-agent-assisted-sdlc/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,945 This file is loaded in full into every session.

When invoked 2,945 The same file — it is already loaded in full.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.02945	$0.02945
Opus 5.5	$0.01178	$0.01178
Sonnet 5.5	$0.00589	$0.00589
Haiku 4.5	$0.00295	$0.00295

Measured 5d ago against content hash e51b1a2cfa31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

sample-agent-assisted-sdlc CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Do not use `curl ... | bash` without downloading to a file first (supply chain risk).

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Do not use `curl ... | bash` without downloading to a file first (supply chain risk).

CLAUDE.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Assisted SDLC

Agentic SDLC platform on Amazon Bedrock AgentCore. GitHub issues → autonomous coding → pull requests.

Commands

npm install                          # Install CDK dependencies
npx cdk synth --quiet                # Validate TypeScript + cdk-nag (run before every commit)
npx cdk deploy --all                 # Deploy all stacks
npx cdk deploy {project}-assistant   # Deploy just the coding assistant stack
npx cdk ls                           # List stacks
npm test                             # Jest snapshot tests

Architecture

6 CDK stacks deployed in order: Infra → SourceControl → ProjectManagement → DeveloperMcp → Gateway → Assistant. Config in sdlc-config.yaml (copy from sdlc-config.template.yaml). Stack names prefixed with project: field from config.

Key paths:

lib/nested/*-stack.ts — stack definitions
lib/constructs/ — reusable CDK constructs
lib/config.ts — config schema + getAssistantDir() mapping
coding-assistants/{claude-code,kiro,codex}/ — container images + plugins
project-management/shared/assistants/ — per-assistant invocation strategies
gateway/developer-mcp-servers/ — developer tool MCP servers (FastMCP)

Languages by Directory

Directory	Language	Package Manager
`lib/`, `bin/`	TypeScript (strict, NodeNext)	npm
`gateway/gateway-iam-proxy/`	Node.js (ESM)	npm
`project-management/shared/`	Python 3.12	pip (requirements.txt)
`project-management/github/mcp/`	Python 3.12 + Go (github-mcp-server binary)	uv
`source-control/github/mcp/`	Python 3.12 + Go	uv
`gateway/developer-mcp-servers/`	Python 3.12 (FastMCP)	uv
`coding-assistants/*/runtime/`	Python 3.12 (FastAPI health server)	uv or pip
`coding-assistants/claude-code/plugin/hooks/`	Bash	—
`test-scripts/`	Bash	—

Conventions

CDK constructs use cdk-nag (AWS Solutions checks). Suppress with NagSuppressions.addResourceSuppressions() and a justification string.
Python formatting: no specific formatter enforced. Follow existing style in each file. ruff check must pass.
TypeScript: strict mode, no implicit any.
Dockerfiles: pin all dependencies (pip install pkg==x.y.z, npm install -g [email protected], git clone --branch vX.Y.Z).
MCP servers use FastMCP with streamable-http transport on port 8000.
Health servers use FastAPI on port 8080 (/ping, /health, /invocations).
Python logging: never call print(). Import get_logger from shared/log.py (or the runtime-local duplicate) and emit structured records. Use %-style messages (logger.info("event %s", value)); pass structured fields via extra={...}. The canonical secret-redaction helper is redact() from shared/log.py. Process-boundary catch-alls (Lambda handler, FastMCP tools) use logger.exception and return a structured error; everything else raises a named exception (WorkspaceSetupError, RuntimeCommandError, TokenError — see shared/errors.py).
Runtime images that build with s3_assets.Asset({path: <runtime-dir>}) carry a duplicate log.py in the runtime directory. The canonical file is project-management/shared/log.py; each duplicate has a "DUPLICATE OF — keep in sync" banner at the top.

Read the full file on GitHub · 172 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.

5d ago First seen · 172 lines · 2,945 tokens per session scan C e51b1a2cfa31

Subscribe to this mod's changes

sample-agent-assisted-sdlc CLAUDE.md is an instructions file published in the GitHub repository aws-samples/sample-agent-assisted-sdlc (47 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,945 tokens to every session, about $0.0118 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.

Building agents Cloud DevOps and cloud

plan-forge naming.instructions.md

Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.

srnichols/plan-forge · 1,453 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

sample-agent-assisted-sdlc: Instructions file for Claude Code