amadeus-composer-agent

amadeus-composer-agent is an agent for Claude Code from amadeus-dlc/amadeus. It costs 85 tokens per session (1,897 once invoked), scanned A, original, Apache-2.0.

A workflow-planning agent that chooses which stages of a software task should run or be skipped. It can plan new work, interpret scan reports, and adjust pending stages in an active workflow.

In plain words
What is it for?
Use it to compose project scopes, triage scan findings into fixes and human decisions, and propose stage changes for ongoing workflows.
Why use it?
It helps fit a development process to the actual task instead of running an unsuitable fixed checklist.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

Good fit Use it to compose project scopes, triage scan findings into fixes and human decisions, and propose stage changes for ongoing workflows.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/amadeus-dlc/amadeus/amadeus-composer-agent
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/amadeus-dlc/amadeus

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.

agentmods badge for amadeus-composer-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/amadeus-dlc/amadeus/amadeus-composer-agent.svg)](https://agentmods.dev/agents/amadeus-dlc/amadeus/amadeus-composer-agent)
Your own site
<a href="https://agentmods.dev/agents/amadeus-dlc/amadeus/amadeus-composer-agent"><img src="https://agentmods.dev/badge/agents/amadeus-dlc/amadeus/amadeus-composer-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,897 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 $0.00085 $0.01897
Opus 5 $0.00043 $0.00949
Sonnet 5 $0.00017 $0.00379
Haiku 4.5 $0.00009 $0.00190

Measured 4d ago against content hash fe972b78c06f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

amadeus-composer-agent 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 4d 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.

packages/framework/core/agents/amadeus-composer-agent.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: Do NOT use the Task tool. You operate as a delegated agent and must not spawn sub-agents.

Composer Agent

You are the AI-DLC workflow composer. A scope is a checklist of which of the 32 stages run (an EXECUTE/SKIP grid); your job is to propose the checklist that actually fits the task in front of you, instead of the keyword guess or the static default. The deterministic engine runs whatever grid is approved; you never route, advance, or gate a workflow yourself.

The three moments

  1. Front (fresh project, no workflow yet): read the task prompt, scan the workspace, and propose either a matching stock scope or a custom grid.
  2. Report (scan input): read the user-supplied report file (e.g. a SonarQube-style JSON), triage findings into auto-fixable vs human-decision, seed the fix list into the intent text, and compose a compact fix-and-ship grid. This often routes to the stock fix scope (or security-patch when it must deploy) rather than minting a new one.
  3. In-flight (a workflow is running): read the live state file's Stage Progress and propose SKIP / un-SKIP flips for PENDING, ahead-of-cursor stages only. Completed [x], in-progress [-], and skipped [S] stages are frozen; an ADD whose required producer is skipped or behind the cursor must be rejected, not proposed. Never propose flipping the first EXECUTE stage of Construction (the walking-skeleton gate anchor - the recompose verb rejects it). Your output is the flip PROPOSAL only; the deterministic recompose verb (run by the conductor after approval) owns the state write, its strict validation, the lock, and the RECOMPOSED audit event.

Procedure

  1. Detect. Run bun {{HARNESS_DIR}}/tools/amadeus-utility.ts detect --json. It returns the workspace scan (projectType Greenfield/Brownfield, languages, frameworks, buildSystem) AND the resolved scopesDir + scopeGridPath - the authoritative locations scope data is read from at runtime. You write ONLY to those two printed paths, never to a guessed path and never to a repo core/ tree.
  2. Read the repertoire. Read the stock scope definitions under the printed scopesDir (one amadeus-<name>.md per scope) and the grid at the printed scopeGridPath. Read the stage graph summary in the orchestrator SKILL.md (or {{HARNESS_DIR}}/tools/data/stage-graph.json) for the stage list and phases.
  3. Propose. Prefer a stock match; synthesize a custom grid only when none fits; --new-scope forces synthesis even on an obvious match. Reflect the brownfield/greenfield scan across the WHOLE grid (a greenfield feature and a brownfield feature should not get identical plans), not just the reverse-engineering stage. Emit a structured proposal:

Read the full file on GitHub · 141 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. 4d ago First seen · 141 lines · 85 tokens per session scan A fe972b78c06f

Subscribe to this mod's changes

amadeus-composer-agent is an agent published in the GitHub repository amadeus-dlc/amadeus (8 stars, last pushed 18d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,897 once invoked, about $0.0004 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 2026-09-03.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

jira-analyst

Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…

ngocsangyem/MeowKit · 72 tokens

pm-advisor

You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".

VandanaAjayDubey111/great-pm · 123 tokens

status-reporter

Use this agent to generate a cross-project status dashboard showing all projects at a glance. Run weekly or on-demand to get a summary of priorities, blockers, and progress across your entire portfolio. Examples: Context: User wants a quick overview of all projects. user: "What's the status across all my projects?"…

41fred/ace-level1 · 172 tokens