composer-researcher

composer-researcher is an agent for Claude Code from FrkAk/piyaz. It costs 216 tokens per session (5,603 once invoked), scanned A, original, AGPL-3.0.

A research agent used in the first phase of a Piyaz task pipeline. It gathers project context, checks current library documentation, and examines the codebase before implementation planning.

In plain words
What is it for?
Use it when a Piyaz project needs grounded research before a feature or code change is planned. It prepares context for the later planning and implementation stages.
Why use it?
It reduces the risk of planning from incomplete task details, outdated library knowledge, or a poor understanding of the existing code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the piyaz plugin — 1 skill, 10 agents, 1 MCP server shipped together

Good fit Use it when a Piyaz project needs grounded research before a feature or code change is planned. It prepares context for the later planning and implementation stages.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frkak/piyaz/composer-researcher
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/FrkAk/piyaz

Made for: Claude Code.

Or install piyaz, the plugin that ships this one along with the rest of its 1 skill, 10 agents, 1 MCP server.

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 composer-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/frkak/piyaz/composer-researcher/github.svg)](https://agentmods.dev/agents/frkak/piyaz/composer-researcher)
Your own site
<a href="https://agentmods.dev/agents/frkak/piyaz/composer-researcher"><img src="https://agentmods.dev/badge/agents/frkak/piyaz/composer-researcher/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 composer-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/frkak/piyaz/composer-researcher"><img src="https://agentmods.dev/badge/agents/frkak/piyaz/composer-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 216 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,603 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 unknown 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 $0.00216 $0.05603
Opus 5 $0.00108 $0.02802
Sonnet 5 $0.00043 $0.01121
Haiku 4.5 $0.00022 $0.00560

Measured 10d ago against content hash bba8204918b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

composer-researcher 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 10d 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.

plugins/claude-code/agents/composer-researcher.md · 245 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 10d ago First seen · 245 lines · 216 tokens per session scan A bba8204918b7

Subscribe to this mod's changes

composer-researcher is an agent published in the GitHub repository FrkAk/piyaz (189 stars, last pushed 8d ago), licensed AGPL-3.0. It adds 216 tokens to every session and 5,603 once invoked, about $0.0011 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.

Related

Other agents, from other repositories

harness-compliance-reviewer

Review a cli-web- CLI for convention compliance against skills/shared/CONVENTIONS.md. Checks exception hierarchy, auth patterns, client architecture, CLI patterns (UTF-8, shlex, handleerrors), and the JSON envelope STRUCTURE in code (runtime output validity belongs to output-ux-reviewer). Returns scored findings. Use…

ItamarZand88/CLI-Anything-WEB · 80 tokens

backend-architect

Design reliable backend systems with focus on data integrity, security, and fault tolerance.

NikiforovAll/claude-code-rules · 19 tokens

planner

Implementation planning specialist using deep reasoning. Creates detailed, actionable plans for features. ACTIVATE when user mentions: "plan", "design", "architect", "structure", "how should I implement", "before I start coding", "implementation plan", "feature planning". Uses Opus for complex architectural reasoning…

anilcancakir/claude-code-plugins · 79 tokens

doc-updater

Documentation specialist for updating inline docs (PHPDoc, JSDoc, TSDoc, VueDoc, DartDoc) and project documentation. Use when code changes need documentation updates. Fast and efficient for doc tasks.

anilcancakir/claude-code-plugins · 47 tokens

brand-architect

Brand identity specialist for creating comprehensive brand guidelines using Jungian archetypes. Use for creating brand.md, defining brand identity, selecting color palettes, establishing voice and tone, or analyzing existing brand assets.

anilcancakir/claude-code-plugins · 43 tokens

market-researcher

Deep market analysis specialist for TAM/SAM/SOM calculation, industry dynamics, and competitive intelligence. Use for comprehensive market sizing, Porter's Five Forces analysis, and identifying growth drivers. Invoke when users need market opportunity assessment, industry structure analysis, or detailed competitive…

anilcancakir/claude-code-plugins · 59 tokens