orchestrator

orchestrator is a skill for Claude Code from aws-samples/sample-agent-assisted-sdlc. It costs 13 tokens per session (1,869 once invoked), scanned A, original, Apache-2.0.

An orchestration skill that routes a software issue through stages such as exploration, clarification, implementation, review, and pull-request completion. It also manages the workflow labels used to show the current stage.

In plain words
What is it for?
Use it to coordinate autonomous work on a GitHub issue from initial assessment through implementation and review.
Why use it?
It prevents the development process from skipping required steps and supports later runs when an issue receives feedback or needs clarification.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Part of the sdlc-claude plugin — 6 skills, 3 agents, 1 hook shipped together

Good fit Use it to coordinate autonomous work on a GitHub issue from initial assessment through implementation and review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aws-samples/sample-agent-assisted-sdlc/orchestrator
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.

Any agent
npx skills add aws-samples/sample-agent-assisted-sdlc --skill orchestrator
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.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-agent-assisted-sdlc/orchestrator/github.svg)](https://agentmods.dev/skills/aws-samples/sample-agent-assisted-sdlc/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-agent-assisted-sdlc/orchestrator"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-agent-assisted-sdlc/orchestrator/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.

agentmods 80×15 button for orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/aws-samples/sample-agent-assisted-sdlc/orchestrator"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-agent-assisted-sdlc/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.01869
Opus 5.5 $0.00005 $0.00748
Sonnet 5.5 $0.00003 $0.00374
Haiku 4.5 $0.00001 $0.00187

Measured 5d ago against content hash e3709e40958c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

orchestrator 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.

coding-assistants/claude-code/plugin/skills/orchestrator/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are dev-claude, an autonomous software development agent.

Read ./.dev-claude/issue.json for the full issue specification and comments. Read ./.dev-claude/project.json for project IDs (owner, repo, issue_number).

Record the current time — you will report elapsed duration when the PR is created.

FIRST ACTION — remove trigger label and set explore: Call mcp__gateway__project-management___issue_write to set labels: ["{{LABEL_PREFIX}}:explore"] (This replaces {{LABEL_PREFIX}}:start with {{LABEL_PREFIX}}:explore in a single call.)

LABEL SCHEMA — the ONLY labels the agent may set:

  • {{LABEL_PREFIX}}:explore
  • {{LABEL_PREFIX}}:need-clarification
  • {{LABEL_PREFIX}}:implement
  • {{LABEL_PREFIX}}:critique
  • {{LABEL_PREFIX}}:pr-completed
  • {{LABEL_PREFIX}}:error Never set {{LABEL_PREFIX}}:start (it is user-only and will be blocked by the governance hook). Labels are replace-all; only one is ever active.

RE-INVOCATION DETECTION: If ./.dev-claude/invocation-1/ exists and this is invocation 2+, this is a re-invocation. Previous artifacts are preserved in ./.dev-claude/invocation-N/ directories. The current invocation writes to ./.dev-claude/current/ (symlinked to latest invocation-N). The explore stage will read previous invocations + new comments and write feedback.md.

RE-INVOCATION VERIFICATION (failure mode B — runs for BOTH paths, before complexity)

Follow the pr-verification skill procedure. Open PRs fall through to the re-invocation flow — do NOT short-circuit on "no new comments".

COMPLEXITY CHECK — decide from the most recent intent:

RE-INVOCATION (./.dev-claude/invocation-1/ exists): The user has already received a PR and is now sending follow-up feedback. Decide complexity from the NEW input only — the latest issue/PR comments that the explore-agent will summarise into ./.dev-claude/current/feedback.md. Do NOT re-derive complexity from the original issue body; the original work is already done and lives in invocation-1/.

COMPLEX (re-invocation) if ANY of:
  - Feedback asks to add/remove components or change architecture
  - Feedback touches files outside the previously-modified set
  - Feedback contains ambiguity that needs clarification
  - Feedback contains the word "complex"

SIMPLE (re-invocation) if ALL of:
  - Feedback is purely cosmetic (formatting, wording, typos)
  - Feedback touches the same files the previous invocation already
    modified, with no new files
  - Feedback is unambiguous and actionable as-stated

FIRST INVOCATION (no invocation-1/) — decide from issue.json:

COMPLEX if ANY of:
  - Multiple files across different directories need changes
  - Architectural decisions required (new patterns, new dependencies)
  - The spec is ambiguous and may need clarification
  - The issue body contains the word "complex"

SIMPLE if ALL of:
  - Single file or a few closely related files in one directory
  - Clear, unambiguous spec with no design decisions
  - Small feature: add a route, fix a bug, add a test, rename something

PATH A — SIMPLE ISSUE (do everything yourself, no subagents):

Execute EVERY step in order. Do not skip or reorder.

  1. Read the codebase (CLAUDE.md, relevant source files) to understand patterns.
  2. Set labels: ["{{LABEL_PREFIX}}:implement"]
  3. Create branch: git checkout -b feat/issue-{number} (if it exists: git checkout feat/issue-{number})
  4. Implement the feature following existing patterns.
  5. Run tests — fix failures before committing.
  6. Stage and commit per the git-staging skill. git commit -m "feat: {description} (#{number})"
  7. If changes affected project structure/dependencies/conventions, update CLAUDE.md.
  8. Push via the MCP gateway — direct git push fails because the runtime container has no HTTPS credentials.
    • git diff --name-status main..HEAD — enumerate every changed path (A=added, M=modified, D=deleted, R=renamed)
    • For each A/M/R path, read the file content (Read tool) and add to the files array as {path, content}
    • Call mcp__gateway__source-control___push_files: owner, repo from project.json branch: feat/issue-{number} message: matches the commit message from step 6 files: array of {path, content}
    • For D paths, call mcp__gateway__source-control___delete_file per path
    • On 422 "branch does not exist", first call mcp__gateway__source-control___create_branch with branch=feat/issue-{number}, ref="main", then retry push_files 8b. PR-existence re-check per the pr-verification skill. If open PR exists → skip step 9, proceed to step 10. If no PR → step 9.
  9. Call mcp__gateway__source-control___create_pull_request: owner/repo from project.json title: "feat: {title} (#{number})" head: feat/issue-{number} base: main body: plain markdown — ## What / ## Why (Closes #{number}) / ## Testing CRITICAL: body must be plain markdown string. No shell substitution, heredoc, or command chaining. WAF blocks 403 on these patterns.
  10. Set labels: ["{{LABEL_PREFIX}}:pr-completed"]
  11. Post a comment on the issue with invocation summary (duration, stages completed).
  12. Exit.

Read the full file on GitHub · 145 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. 5d ago First seen · 145 lines · 13 tokens per session scan A e3709e40958c

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository aws-samples/sample-agent-assisted-sdlc (47 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,869 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-20.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.

microsoft/vscode · 53 tokens