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/atomgraph/web-algebra/claude-mdgit clone --depth 1 https://github.com/AtomGraph/Web-AlgebraWhat 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 | $0.00897 | $0.00897 |
| Opus 5 | $0.00449 | $0.00449 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
Web-Algebra CLAUDE.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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is LinkedDataHub DSL - a composable RDF operations system that translates natural language instructions into JSON-formatted domain-specific language operations for loading, querying, and writing RDF data.
Core Architecture
The system is built around the Operation abstract base class in src/web_algebra/operation.py which:
- Provides a registry system for all operations via
Operation.registry - Supports both standalone execution (
execute()) and MCP server integration (run()) - Handles recursive JSON execution with
execute_json()that processes nested@opstructures - Operations are auto-discovered from
src/web_algebra/operations/directory
Key Components
- Operation Registry: Operations self-register via
Operation.register()during module import - JSON DSL: Operations use
@opkey withargsfor parameters, supporting nested operation calls - Context System: ForEach operations set row context for inner operations to access via
Var - RDF Integration: Uses
rdflib.Graphinternally, JSON-LD for interchange
Commands
Development
# Install dependencies
poetry install
# Run standalone with JSON file
poetry run python src/web_algebra/main.py --from-json ./examples/example.json
# Run with LinkedDataHub integration
poetry run python src/web_algebra/main.py --from-json ./examples/denmark-cities.json \
--cert_pem_path ../LinkedDataHub/ssl/owner/cert.pem \
--cert_password Marchius
# Run as MCP server
poetry run uvicorn web_algebra.server:server --reload
Operation Development
When adding new operations:
- Inherit from
Operationinsrc/web_algebra/operation.py - Implement required methods:
description(),inputSchema(),execute(),run() - Place in
src/web_algebra/operations/directory for auto-discovery - Use
@opandargsstructure in JSON examples
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.
- 2d ago First seen · 92 lines · 897 tokens per session scan A 5c5eb1d64801
Web-Algebra CLAUDE.md is an instructions file published in the GitHub repository AtomGraph/Web-Algebra (45 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 897 tokens to every session, about $0.0045 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
mcp-sparql AGENTS.md
AGENTS.md instructions for daedalus/mcp-sparql, covering agents.md — mcp-sparql, commands, development, setup and test.
open-ontologies CLAUDE.md
Instructions for fabio-rovai/open-ontologies, covering open ontologies, ontology engineering workflow, generate, validate and load and reason.
togomcp CLAUDE.md
Instructions for dbcls/togomcp, covering togomcp, architecture, data layout, parameter conventions and return-shape and error conventions.
zurich-opendata-mcp CLAUDE.md
Instructions for malkreide/zurich-opendata-mcp, covering project conventions for claude, teil 1 — portfolio-konventionen, vor der arbeit, tests and wenn etwas rot ist.
AgentForge AGENTS.md
AGENTS.md instructions for DataBassGit/AgentForge, covering agentforge agent guide, documentation map, working rules, local environment and change discipline.
ontosphere AGENTS.md
AGENTS.md instructions for ThHanke/ontosphere, covering ontosphere — agent guide, live instance, 200 = ready, mcp tool surface and how to call tools.