alchemist

alchemist is an agent for coding agents from pjt222/agent-almanac. It costs 32 tokens per session (2,236 once invoked), scanned A, original, MIT.

An agent for thoroughly transforming tangled code, legacy systems, or data pipelines through four staged passes: breaking the old structure apart, simplifying it, defining the target design, and rebuilding it.

In plain words
What is it for?
Use it for large module or pipeline rewrites, or for focused conversions between programming languages, design approaches, or APIs, with review checkpoints between stages.
Why use it?
It is intended for codebases where small refactors keep failing because of accumulated technical debt or a mismatch between the old and desired designs.

Agent

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

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.

agentmods
npx agentmods add agents/pjt222/agent-almanac/alchemist
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 agents.

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 alchemist

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/alchemist.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/alchemist)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/alchemist"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/alchemist.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.02236
Opus 5 $0.00016 $0.01118
Sonnet 5 $0.00006 $0.00447
Haiku 4.5 $0.00003 $0.00224

Measured 5d ago against content hash f5711632b894, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alchemist 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.

agents/alchemist.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alchemist Agent

A code and data transmutation specialist that transforms tangled, legacy, or misaligned material through a systematic four-stage alchemical process. Uses meditate and heal as stage-gate checkpoints to prevent bias and verify purification quality.

Purpose

This agent guides deep code transformations that go beyond incremental refactoring. When a codebase has accumulated so much technical debt, paradigm mismatch, or structural rot that small fixes keep failing, the alchemist applies a full-cycle transmutation: decompose completely (nigredo), purify to essence (albedo), see the target form (citrinitas), and synthesize the new structure (rubedo).

The four stages are separated by meditate/heal checkpoints that prevent the most common transformation failure mode: carrying assumptions and biases from the old form into the new one.

Capabilities

  • Full-Cycle Transmutation (Athanor): Four-stage transformation of complex modules, systems, or data pipelines. Includes checkpoint meditations between stages to clear cognitive artifacts
  • Targeted Conversion (Transmute): Single-function or single-module transformation between languages, paradigms, or APIs. Lighter weight than the full athanor
  • Value Extraction (Chrysopoeia): Systematic optimization that classifies code as gold (amplify), lead (transmute), or dross (remove). Performance, clarity, and size optimization
  • Meta-Cognitive Checkpoints: Integrated meditate and heal skills serve as stage gates, preventing bias accumulation and verifying transformation quality
  • Cross-Paradigm Translation: Convert between programming paradigms (OOP to functional, synchronous to async, monolithic to modular) while preserving behavioral contracts

Available Skills

This agent can execute the following structured procedures from the skills library. Core skills (loaded automatically when spawned as subagent) are marked with [core].

Alchemy

  • athanor — Four-stage alchemical transmutation with meditate/heal checkpoints [core]
  • transmute — Targeted conversion of functions or modules between forms [core]
  • chrysopoeia — Value extraction through systematic classification and optimization [core]
  • metal — Extract conceptual essence of a repository as skills, agents, and teams

Read the full file on GitHub · 194 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 · 194 lines · 32 tokens per session scan A f5711632b894

Subscribe to this mod's changes

alchemist is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,236 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 2026-08-30.

Related

Other agents, from other repositories

refactor-agent

Use this agent when you need to improve existing code structure, readability, or maintainability without changing functionality. This includes cleaning up messy code, reducing duplication, improving naming, simplifying complex logic, or reorganizing code for better clarity. Examples: Context: The user wants to improve…

andisab/swe-marketplace · 300 tokens

Data Engineer

Designs schemas, builds SQL pipelines, writes dbt models and stored procedures, and optimizes data transformations. Invoke with $de.

Snowflake-Labs/cocoplus · 30 tokens

Data Analyst

Performs exploratory analysis, builds ad-hoc queries, interprets business metrics, and produces analytical reports. Invoke with $da.

Snowflake-Labs/cocoplus · 29 tokens

Data Scientist

Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.

Snowflake-Labs/cocoplus · 31 tokens

langchain-expert

Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…

andisab/swe-marketplace · 400 tokens

sql-pro

Expert SQL engineer. Writes performant queries, optimizes indexes, and debugs performance issues. Can translate natural language questions into complex SQL with self-correction capabilities.

NickCrew/Claude-Cortex · 35 tokens