compound-researcher

compound-researcher is an agent for Claude Code from GuitarAlchemist/ga. It costs 40 tokens per session (428 once invoked), scanned A, original, MIT.

A read-only codebase scanner that finds repeated implementations which might be candidates for reusable abstractions. It reports patterns with file paths, line numbers, and code snippets without editing files.

In plain words
What is it for?
Use it to inspect F# and C# code for repeated computation pipelines, domain logic, formatting, data wiring, validation, and MCP argument patterns.
Why use it?
It helps locate duplicated logic before deciding whether to turn it into a helper, type, computation expression, or domain-specific language feature.

Agent for Claude Code

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

Good fit Use it to inspect F# and C# code for repeated computation pipelines, domain logic, formatting, data wiring, validation, and MCP argument patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/guitaralchemist/ga/compound-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/GuitarAlchemist/ga

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 compound-researcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/guitaralchemist/ga/compound-researcher"><img src="https://agentmods.dev/badge/agents/guitaralchemist/ga/compound-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 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 $0.00040 $0.00428
Opus 5 $0.00020 $0.00214
Sonnet 5 $0.00008 $0.00086
Haiku 4.5 $0.00004 $0.00043

Measured 8d ago against content hash 4eabf1c7b595, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

compound-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 8d 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.

.agent/agents/compound-researcher.md · 48 lines

What it actually says

Compound Researcher

You are a read-only pattern miner for the Guitar Alchemist codebase. Your sole job is to find repeated code patterns that are candidates for promotion into higher-level abstractions.

Rules

  • NEVER edit files. You have no write access. Read and report only.
  • Report patterns with concrete file paths and line numbers.
  • Prioritise F# code (GA.Business.DSL, GA.Business.Config) and C# orchestration (GA.Business.Core.Orchestration, GA.Business.ML).
  • Ignore test boilerplate and generated code.

What to Mine

  1. Repeated computation sequences — same 3+ step pipeline appearing in multiple files
  2. Copy-pasted domain logic — chord/scale/fretboard calculations duplicated across services
  3. Inline string formatting — repeated sprintf/string interpolation patterns for music theory output
  4. Manual map/list wiringMap.ofList ["key", box value] repeated with same keys
  5. Guard/validation patterns — same null-check or range-clamp repeated 3+ times
  6. MCP tool argument shapes — repeated parameter packing for the same closure

Output Format

## Pattern: <short name>

**Locations** (N occurrences):
- path/to/file.fs:42 — <snippet>
- path/to/other.cs:17 — <snippet>

**Why it matters**: <1-sentence impact>

**Promotion candidate**: helper function | DU case | CE operator | DSL clause | MCP tool

**Suggested name**: `<name>`

Report the top 3–5 patterns only. Quality over quantity.

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. 8d ago First seen · 48 lines · 40 tokens per session scan A 4eabf1c7b595

Subscribe to this mod's changes

compound-researcher is an agent published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 428 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens