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 skills/colaberry/worldoftaxonomy/anthropicnpx skills add colaberry/WorldOfTaxonomy --skill anthropicgit clone --depth 1 https://github.com/colaberry/WorldOfTaxonomyWrote 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/skills/colaberry/worldoftaxonomy/anthropic)<a href="https://agentmods.dev/skills/colaberry/worldoftaxonomy/anthropic"><img src="https://agentmods.dev/badge/skills/colaberry/worldoftaxonomy/anthropic.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 | $0.00117 | $0.01262 |
| Opus 5 | $0.00059 | $0.00631 |
| Sonnet 5 | $0.00023 | $0.00252 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
worldoftaxonomy 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WorldOfTaxonomy Skill
What this does
Turns any free-text question about industry, occupation, medical, trade, or regulatory classification into a grounded answer backed by 1,000+ official taxonomies linked as a single knowledge graph.
When to invoke
Use this skill when the user wants to:
- Assign a standard code to a business description, product, occupation, diagnosis, or document
- Translate a code between systems (NAICS 2022 <-> ISIC Rev 4, SOC 2018 <-> ISCO-08, ICD-10-CM <-> ICD-10-GM, HS 2022 <-> CPC v2.1, etc.)
- Find every cross-system equivalent of a given code
- Browse hierarchy (children, ancestors, siblings, subtree) of a system
- Compare two systems' coverage or structure
- Audit data provenance and crosswalk density across systems
Do NOT invoke for general explanations of what NAICS/ISIC/ICD are - answer from general knowledge unless the user wants live data.
How to use
Primary: REST API
Base URL: https://worldoftaxonomy.com/api/v1
Auth: Authorization: Bearer wot_<32hex> (get a key at https://worldoftaxonomy.com/dashboard).
Anonymous access works at 30 req/min; authenticated keys get 1000-50000 req/min depending on tier.
Core endpoints:
GET /systems # list systems
GET /systems/{id} # detail + roots
GET /systems/{id}/nodes/{code} # node detail
GET /systems/{id}/nodes/{code}/children
GET /systems/{id}/nodes/{code}/ancestors
GET /systems/{id}/nodes/{code}/siblings
GET /systems/{id}/nodes/{code}/equivalences # crosswalk edges
GET /search?q=<term>&system=<optional>
POST /classify # body: {"description": "..."}
GET /equivalences/stats # coverage matrix
OpenAPI spec: https://worldoftaxonomy.com/api/v1/openapi.json
Secondary: MCP server
For MCP-aware clients, install world_of_taxonomy from the GitHub repo and run python -m world_of_taxonomy mcp as a stdio server. Tools include classify_business, translate_code, translate_across_all_systems, get_equivalences, get_crosswalk_coverage, get_system_diff, explore_industry_tree, and list_crosswalks_by_kind.
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 · 88 lines · 117 tokens per session scan A 7a38fea9090b
worldoftaxonomy is a skill published in the GitHub repository colaberry/WorldOfTaxonomy (9 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,262 once invoked, about $0.0006 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.
Other skills, from other repositories
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
pagefly
Connect to your self-hosted PageFly knowledge base. Query documents, search, upload files, read content, and chat with your AI agent — all from Claude Code.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.
trend
Analyzes knowledge base growth patterns, identifies emerging themes, and produces trend insight articles.
session-ingest
Ingest a coding session JSONL into AKB as structured notes — session report + parallel-drafted TIL / task / idea / decision sub-notes. Auto-discovers the current session's JSONL when no positional path is given (Claude / Codex). --delegate {target} fires the work to another target's CLI and exits.
akb-query
Answer a question from the AKB vault — decompose, search (hybrid / graph), ground in compiled-truth-over-timeline precedence, and synthesize a cited answer with gap/conflict/stale flags. Read-only.