sparq: Skill for Claude Code

.claude/skills/noir-circuit-patterns/SKILL.md

noir-circuit-patterns is a skill for Claude Code from sparq-org/sparq. It costs 99 tokens per session (4,107 once invoked), scanned A, original, MIT.

A collection of coding patterns for Noir circuits that prove SPARQL queries were evaluated correctly over committed RDF graphs. RDF is a data format for facts linked as subject, predicate, and object; SPARQL is its query language.

In plain words
What is it for?
Use it when implementing graph matching, joins, filters, projections, hashing, or other SPARQL operations in Noir circuits.
Why use it?
It helps avoid recurring circuit and language mistakes while keeping commitments, public inputs, witnesses, and proof soundness connected correctly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sparq-org/sparq's own configuration. It tells Claude Code how to work on sparq itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sparq configures →

Part of the sparq plugin — 55 skills, 20 agents, 2 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to sparq-org/sparq. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sparq-org/sparq/main/.claude/skills/noir-circuit-patterns/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sparq-org/sparq

Made for: Claude Code.

Or install sparq, the plugin that ships this one along with the rest of its 55 skills, 20 agents, 2 hooks.

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 noir-circuit-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/sparq-org/sparq/noir-circuit-patterns/github.svg)](https://agentmods.dev/skills/sparq-org/sparq/noir-circuit-patterns)
Your own site
<a href="https://agentmods.dev/skills/sparq-org/sparq/noir-circuit-patterns"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/noir-circuit-patterns/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.

agentmods 80×15 button for noir-circuit-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/sparq-org/sparq/noir-circuit-patterns"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/noir-circuit-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,107 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00099 $0.04107
Opus 5 $0.00049 $0.02054
Sonnet 5 $0.00020 $0.00821
Haiku 4.5 $0.00010 $0.00411

Measured 10d ago against content hash e0d231119a23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

noir-circuit-patterns 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 10d 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.

.claude/skills/noir-circuit-patterns/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Noir circuit patterns for ZKP-SPARQL

Reusable patterns for the Noir circuits that prove correct SPARQL evaluation over committed RDF graphs. These are starting points; verify any specific syntax via the /noir-lang/noir context7 docs before pasting into code.

For generic Noir guidance the upstream skills cover better: noir-developer for circuit structure / stdlib / workspace setup, noir-idioms for the idiomatic ACIR-vs-Brillig style, noir-testing for the testing framework. This skill is intentionally narrow to: SPARQL-domain patterns (BGP, joins, filters, triple commitments), plus the Noir-language gotchas this codebase has hit specifically (orphan rule, pub(crate) for verifier-hint soundness, trait associated constants in const-generic positions, IEEE-754 total_compare vs Ord, witness-vs-comptime branches). For cost analysis on a candidate gadget see the sister skill noir-optimisation.

Always-do

  • Pin the toolchain. Nargo.toml declares compiler_version. README of the circuit dir documents the matching bb version.
  • Query context7 first. Before guessing a stdlib function name, a trait bound, or a generic syntax, run mcp__context7__query-docs against /noir-lang/noir. The Noir language has evolved fast; recall is unreliable.
  • Document main's public inputs. A commented-out line per public input naming what it commits to and why.
  • Test every primitive. Noir supports #[test] in source — use it. Cover an accept case and at least one reject case.
  • Comment constraint cost. When writing a non-trivial gadget, estimate where the dominant cost lies (hashing? bit-decompositions? range proofs?) and note it.

Triple commitment patterns

The credential graph is committed before the circuit consumes it. The two natural shapes:

  • Per-triple Pedersen / Poseidon hash, accumulated into a Merkle tree. The prover supplies a triple + a Merkle path; the circuit verifies the path against a public root. Best when triples are accessed sparsely (e.g. BGP with few patterns).
  • Sorted sequence committed via a single sponge hash. The prover supplies the full ordered triple list; the circuit re-hashes and asserts equality with a public commitment. Best when most of the graph is touched anyway, or when sortedness is needed downstream (e.g. for sort-merge joins).

Read the full file on GitHub · 419 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. 10d ago First seen · 419 lines · 99 tokens per session scan A e0d231119a23

Subscribe to this mod's changes

noir-circuit-patterns is a skill published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 4,107 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

signature-replay

Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.

PurpleAILAB/Decepticon · 31 tokens

official-sui-skills

Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…

MystenLabs/sui · 116 tokens

crypto-market-rank

Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…

tradecatlabs/tradecat-public · 85 tokens

trading-signal

Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…

tradecatlabs/tradecat-public · 64 tokens

bridge

Cross-chain token transfers using Wormhole and CCTP.

alsk1992/CloddsBot · 13 tokens

onchainkit

Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.

alsk1992/CloddsBot · 24 tokens