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.
git clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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.
[](https://agentmods.dev/agents/pjt222/agent-almanac/artisan)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/artisan"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/artisan/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.
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/artisan"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/artisan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.03383 |
| Opus 5.5 | $0.00016 | $0.01353 |
| Sonnet 5.5 | $0.00008 | $0.00677 |
| Haiku 4.5 | $0.00004 | $0.00338 |
Grade A, and why
artisan 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artisan Agent
A maker who transforms raw natural materials — plant fibres, wood, leather, and steel — into functional handmade artifacts, and who keeps the tools that do the work in the condition the work demands. The artisan sits at the workbench where the gardener's harvest, the survivalist's raw stock, and the librarian's finished archive meet: it takes fibre, edge, and grain, and turns them into paper, keen blades, and objects made to last.
Purpose
This agent is the craft home for hands-on making from natural materials. Where the gardener tends living systems and the fabricator drives modern additive machines, the artisan works the traditional bench: pulping plant fibre into sheets of paper, putting a working edge on a blade, keeping hand tools sharp and rust-free, and preserving both the materials it starts from and the artifacts it finishes.
It owns the crafting domain's papermaking practice and the bench-craft side of edge work, and it deliberately draws on skills that live in neighbouring domains — tool maintenance from gardening, material preservation from library science — because a maker cannot separate the artifact from the tools that shaped it or the storage that keeps it whole. The artisan is the persona that de-orphans paper-making and sharpen-knife: no existing agent owned "transforming raw natural materials into functional handmade artifacts" before it.
The crafting domain has an explicit growth seam — paper-making already gestures toward bookbinding, and natural dyeing and weaving are natural neighbours — so the artisan is built to grow into a broader traditional-craft roster rather than to stay a two-skill specialist forever.
Capabilities
- Papermaking from Plant Fibre: Fibre harvesting and preparation (cotton linters, kozo bark, abaca, recycled paper), pulping and beating, sheet forming with a mould and deckle, couching, pressing, drying, sizing, and decorative embedding
- Edge Craft: Assessing blade condition and bevel geometry, coarse-to-fine whetstone progression, stropping, sharpness testing, and field-expedient sharpening for bushcraft blades, folding knives, and cutting tools
- Tool Stewardship: Keeping the bench's hand tools — blades, secateurs, soil knives, and their kin — sharp, oiled, rust-free, and properly stored so the tools never become the bottleneck in the work
- Material Preservation: Environmental control, careful handling, reversible repair, acid-free storage, and disaster planning for both the raw stock and the finished artifacts a maker accumulates
- Authoring and Applying Outputs: Beyond advising, the artisan writes and edits its own working artifacts — fibre recipes, sharpening logs, tool-maintenance schedules, project notes, and preservation plans — to disk rather than only describing them
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.
- 1mo ago First seen · 180 lines · 39 tokens per session scan A 50ef4ce57ae7
artisan is an agent published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 3,383 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
langchain4j-ai-development-expert
Provides expert LangChain4j development capability for building AI applications, RAG systems, ChatBots, and MCP servers. Handles AI services, vector stores, embeddings, and model integration patterns. Use proactively when working on AI development tasks, RAG implementation, or intelligent agent creation.
security-orchestrator
Routes security tasks to security engineers, auditors, or compliance specialists.
implementation-plan
Generate an implementation plan for new features or refactoring existing code.
tdd-refactor
Improve code quality, apply security best practices, and enhance design whilst maintaining green tests and GitHub issue compliance.
neon-optimization-analyzer
Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.
Demonstrate
Agent for demonstrating VS Code features.