sparq AGENTS.md

sparq AGENTS.md is an instructions file for Codex, OpenCode from sparq-org/sparq. It costs 47,264 tokens per session, scanned F, original, MIT.

Repository instructions for coding agents working with sparq, a Rust database engine that stores linked data and answers SPARQL queries. They also describe sparq's code, skills, contributor workflow, and shared testing system.

In plain words
What is it for?
Helping agents work on sparq, use its code and skills, track tasks, follow repository conventions, and contribute to its shared evaluation system.
Why use it?
They give an agent the project context and working rules needed to make safe, consistent changes in a large repository.

Instructions file for CodexOpenCode

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 instructions/sparq-org/sparq/agents-md
Clone the repo
git clone --depth 1 https://github.com/sparq-org/sparq

Made for: Codex, OpenCode.

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 sparq AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sparq-org/sparq/agents-md.svg)](https://agentmods.dev/instructions/sparq-org/sparq/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sparq-org/sparq/agents-md"><img src="https://agentmods.dev/badge/instructions/sparq-org/sparq/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 47,264 This file is loaded in full into every session.
When invoked 47,264 The same file — it is already loaded in full.
Security scan F 4 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 $0.47264 $0.47264
Opus 5 $0.23632 $0.23632
Sonnet 5 $0.09453 $0.09453
Haiku 4.5 $0.04726 $0.04726

Measured yesterday against content hash 323dd6196eb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

sparq AGENTS.md scanned grade F with 4 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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **Ephemeral bench/bootstrap scripts are exempt from hash-pinning.** The throwaway self-terminating EC2 bench/hardware-run scripts (`scripts/aws-bootstrap.sh`, `hwrun/*.sh`, `bench/**/remote.sh`) `curl … | sh` rustup an

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **NEVER arm auto-merge on a STACKED PR (base ≠ `main`).** <!-- [OPUS-4.8] sq-u59rq: the stacked-PR auto-merge trap, #1023 → #1028 --> When you chain PR *B* onto PR *A*'s branch to dodge a re-conflict — i.e. *B*'s base

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

**Where this runs — the session executes ON an AWS EC2 instance (the persistent work box).** <!-- [OPUS-4.8] execution-environment clarification --> The orchestrator and every sub-agent run on an EC2 instance (confirm wi

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Ephemeral bench/bootstrap scripts are exempt from hash-pinning.** The throwaway self-terminating EC2 bench/hardware-run scripts (`scripts/aws-bootstrap.sh`, `hwrun/*.sh`, `bench/**/remote.sh`) `curl … | sh` rustup an
AGENTS.md · 880 lines

How it starts

The opening of the file, as written. The whole thing — 880 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — sparq

A README for coding agents. If you are an AI agent working on or with this repo, read this first.

[CONTEXT-ECONOMY] Worker-tier core available

Codex worker tier: The worker-essential rules (sub-agent shared contract, maintenance rule, task tracking, repository hygiene) are now available in AGENTS-worker-core.md — a ≤32 KiB subset that fits the codex project_doc_max_bytes cap. The full AGENTS.md (this file, ~144 KB) remains the authoritative reference for the complete contract and orchestrator documentation; every rule in the worker core is reachable via linked sections below.

What sparq is

sparq is a from-scratch RDF triplestore and SPARQL 1.1 engine in Rust — dictionary-encoded, six sorted permutation indexes, parallel + streaming execution, RDFS/OWL-RL/N3 inference, an out-of-core (mmap) mode with a compressed on-disk format, a WebAssembly build, and a W3C-conformant HTTP server. The engine is published across several surfaces:

  • Rust crates (crates.io): sparq-core, sparq-engine (core), sparq-cli, sparq-server, plus opt-in capability crates (sparq-reason, sparq-reason-el, sparq-shacl, sparq-geo, sparq-text, sparq-rsp, sparq-hdt, sparq-solid, sparq-arrow, sparq-mcp, sparq-vc, ...). sparq-reason-el is a separate opt-in crate (depending on it is the opt-in): an OWL 2 EL consequence-based classifier that computes the complete rdfs:subClassOf subsumption lattice that OWL 2 RL (sparq-reason) is sound but silently incomplete for — see skills/inference/SKILL.md.
  • In-workspace, publish = false server estate (NOT on crates.io): sparq-lws-core — an EXPERIMENTAL native Solid/LDP (Linked Web Storage) server core imported from jeswr/solid-server-rs, SPARQ-authoritative for RDF + WAC, with Solid-OIDC/DPoP auth delegated to the pinned solid-oidc-verifier. It does not replace the TypeScript prod-solid-server and its default storage is ephemeral. sparq-lws-wasm is its opt-in wasm adapter (the local-development host behind @sparq-org/solid-server), and sparq-wac-oracle is the server-independent WAC/ACP decision test-vector corpus. Usage: skills/solid-lws-server/SKILL.md; design decisions: research/lws-design-records.md.
  • npm: @sparq-org/sparq — RDF/JS-typed API over the wasm build, zero runtime deps; [GPT-5.6] @sparq-org/solid-server — loopback-only Solid/LDP development host over the separate in-memory wasm adapter, with fixed-owner default and opt-in Node-side Solid-OIDC verification.
  • PyPI: sparq-rdf (import name sparq) — pyo3/maturin bindings.

Read the full file on GitHub · 880 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. yesterday Changed · +7 tokens per session 323dd6196eb2
  2. 5d ago First seen · 880 lines · 47,257 tokens per session scan F c62add9f5442

Subscribe to this mod's changes

sparq AGENTS.md is an instructions file published in the GitHub repository sparq-org/sparq (10 stars, last pushed today), licensed MIT. It adds 47,264 tokens to every session, about $0.2363 per session on Opus 5. A static security scan graded it F with 4 findings (downloads and executes remote code, reads agent configuration directories, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.