A coding agent that makes the requested changes in a repository and creates commits, which are saved checkpoints in Git. It can also apply review fixes or respond to later user feedback.

Use it to implement an issue, address critique findings, incorporate feedback, run tests, and commit the resulting code.

It gives the implementation step a defined process: follow the project's patterns, run its tests, fix failures, and save the changes on an issue branch.

implement — Agent for Claude Code by aws-samples

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

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.

Clone the repo

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

Made for: Claude Code.

Or install sdlc-claude, the plugin that ships this one along with the rest of its 6 skills, 3 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.

README.md

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

Your own site

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

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 643 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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	$0.00028	$0.00643
Opus 5.5	$0.00011	$0.00257
Sonnet 5.5	$0.00006	$0.00129
Haiku 4.5	$0.00003	$0.00064

Measured 5d ago against content hash f0613b331f38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

implement scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules cdk.out gateway-iam-proxy/node_modules .ruff_cache /tmp/cdk.out 2>/dev/null

coding-assistants/claude-code/plugin/agents/implement.md · 55 lines

What it actually says

Read in this order:

./.dev-claude/project.json
./.dev-claude/issue.json
./.dev-claude/current/explore.md
./.dev-claude/current/questions.md (if present — contains answered clarifications)
./.dev-claude/current/critique.md (if present — this is a re-implementation pass)
./.dev-claude/current/feedback.md (if present — user feedback from re-invocation)

Set labels: ["{{LABEL_PREFIX}}:implement"] via mcp__gateway__project-management___issue_write.

FIRST RUN (no critique.md and no feedback.md):

Create branch: git checkout -b feat/issue-{number} If the branch already exists: git checkout feat/issue-{number}
Implement the feature, following patterns from explore.md exactly
Run the test command from explore.md — fix any failures before committing
git add <explicit paths> then git commit -m "feat: {description} (#{number})"

SECOND RUN (critique.md exists):

You are already on feat/issue-{number}
Address every point raised in critique.md
Run tests — fix failures
git add <explicit paths> then git commit -m "fix: apply critique (#{number})"

RE-INVOCATION RUN (feedback.md exists):

You are already on feat/issue-{number}
Address every point in feedback.md (user's PR review comments)
Run tests — fix failures
git add <explicit paths> then git commit -m "fix: address feedback (#{number})"

AFTER COMMITTING — RECLAIM DISK SPACE (MANDATORY, 1 GB session cap): The /mnt/workplace mount is hard-capped at 1 GB. Use /tmp for build artifacts (it has ~7 GB on the rootfs overlay and is recycled on microVM restart). When running cdk synth, use --output /tmp/cdk.out to avoid filling session storage.

rm -rf node_modules cdk.out gateway-iam-proxy/node_modules .ruff_cache /tmp/cdk.out 2>/dev/null

AFTER COMMITTING — UPDATE CLAUDE.md IF NEEDED: If your changes affected dependencies, project structure, test command, or conventions, update ./.claude/CLAUDE.md and include it in the commit.

Do not push. Do not open a PR. Exit after committing. Do not modify files outside the feature scope. Do not add dependencies not explicitly required by the spec.

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 · 55 lines · 28 tokens per session scan C f0613b331f38

Subscribe to this mod's changes

implement is an agent published in the GitHub repository aws-samples/sample-agent-assisted-sdlc (47 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 643 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.

Commits Git and workflow

secrets-detector

Detects committed secrets and credentials so they can be removed and rotated. Use to scan a repo defensively before making it public or as a pre-commit safeguard.

JosephHampton/awesome-gemini-cli-subagents · 38 tokens

plastic-node-work

Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.

zalom/plastic · 65 tokens

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

implement