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.
npx agentmods add instructions/machinavitalis/jaxonomy/agents-mdgit clone --depth 1 https://github.com/machinavitalis/jaxonomyWrote 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/instructions/machinavitalis/jaxonomy/agents-md)<a href="https://agentmods.dev/instructions/machinavitalis/jaxonomy/agents-md"><img src="https://agentmods.dev/badge/instructions/machinavitalis/jaxonomy/agents-md.svg" alt="Measured on agentmods" 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 | $0.02244 | $0.02244 |
| Opus 5 | $0.01122 | $0.01122 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
jaxonomy AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Jaxonomy
Agent bootstrap and operational notes, for any coding agent (Claude Code,
Codex, Gemini, Cursor, …) and human contributors. This is the canonical,
tool-neutral entry file; CLAUDE.md, GEMINI.md,
.github/copilot-instructions.md, and CONVENTIONS.md are symlinks to it, and
.cursor/rules/ points here (see "Entry points" at the end).
Two doors, depending on what you're here to do:
- Modifying / adding code in Jaxonomy → follow the read order below,
starting at
AGENTS/README.md. Full project orientation lives inAGENTS/; come back here for the things that specifically save agent time. - Using Jaxonomy's public API in your own code (authoring a tutorial,
building a demo, writing a downstream library) → read
SKILL.md, the consumer operating manual, instead.
Read first
AGENTS/README.md— navigation + which AGENTS file to use when.AGENTS/CONTEXT.md— what Jaxonomy is, design philosophy, key abstractions.AGENTS/PATTERNS.md— coding conventions (npavsjnp,LeafSystemcallback signatures, NamedTuple state, test patterns, naming).AGENTS/DECISIONS.md— ADRs; check before re-litigating a settled choice.AGENTS/RULES.md— operating principles, shippable-surface rule, claims/gaps discipline, self-improvement loop.
For a pure usage session (author a tutorial, build a demo, exercise the public
API), SKILL.md is the better starting point.
Operating discipline (pointers, not a second copy)
The substance lives in two files; this bootstrap defers to them rather than restating them:
AGENTS/RULES.md— the four operating principles (think before coding; simplest implementation that fits; surgical changes only; define success then loop), the shippable-surface rule + adversarial-review pass, claims/gaps discipline, and the self-improvement loop. Read it once.AGENTS/README.md— session protocol, branching/commits, scope discipline, and the autonomy/escalation list.
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.
- 4d ago First seen · 147 lines · 2,244 tokens per session scan A a3b7579f8f6a
jaxonomy AGENTS.md is an instructions file published in the GitHub repository machinavitalis/jaxonomy (19 stars, last pushed 23d ago), licensed MIT. It adds 2,244 tokens to every session, about $0.0112 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.
Other instructions, from other repositories
codex-serverops-mcp AGENTS.md
AGENTS.md instructions for cyyprezz/codex-serverops-mcp, covering serverops project contract and architecture boundaries.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).