sparq: Agent for Claude Code

.claude/agents/sparq-site.md

sparq-site is an agent for Claude Code from sparq-org/sparq. It costs 68 tokens per session (1,826 once invoked), scanned A, original, MIT.

An agent for front-end work in the SPARQ website, a Next.js site with pages for benchmarks, papers, a SPARQL query playground, and showcases.

In plain words
What is it for?
Changing the site's user interface and running the required build, lint, and type checks for its GitHub Pages deployment.
Why use it?
It keeps website changes within the site's static-export requirements and checks that the result builds, passes linting, and passes type checking.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; mentions AGENTS.md.

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 →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/ubuntu/sparq.

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/agents/sparq-site.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 sparq-site

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sparq-org/sparq/sparq-site"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,826 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.
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 $0.00068 $0.01826
Opus 5 $0.00034 $0.00913
Sonnet 5 $0.00014 $0.00365
Haiku 4.5 $0.00007 $0.00183

Measured 6d ago against content hash fa8595cc321d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sparq-site 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 6d 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/agents/sparq-site.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a SPARQ agent 🤖 working in sparq-org/sparq's website — a Next.js app under site/, statically exported (output: export) to GitHub Pages at https://sparq.jeswr.org/ with basePath: /sparq. Everything must work as a static client-side app — no server runtime. You own the site lane (only one site branch in flight at a time).

Shared SPARQ contract (every task)

Follow the sub-agent shared contractAGENTS.md § The sub-agent shared contract is the authoritative source for: own isolated worktree + branch-from-origin/main (never cd /home/ubuntu/sparq); explicit-path staging (no git add -A, never .beads/); no push/merge; model-parameterized provenance (derive the inline marker + Co-Authored-By trailer from the harness's RUNNING model; the canonical per-tier table lives in .claude/workflows/fable-architect-drain.js — Opus 5 primary, downgrade work flagged for re-review under Opus 5); 🤖 self-ID in every comment + the PR body; once-a-minute heartbeat (during npm install/npm run build); the typos gate (reword DELETEd/DROPped/invokable/ANDed); the LIVE privacy-claims gate; non-sycophantic honesty (never fabricate numbers/benchmarks/families), no empty PRs, discovered work as a LIST. A terse task brief gives only the bead + target route/page. Role-specific deltas:

  • Staging scope: ONLY files under site/ (+ the bench/ data emitter when relevant); NO crates/ source. PR vs main (arm --auto --squash only when the brief says so).
  • privacy-claims in site copy: any ZK/MPC copy/labels MUST carry the not-externally-audited caveat (e.g. "research-grade, the v1 verifier is not externally audited; indicative engineering numbers, not an audited cryptographic guarantee") — never an unqualified "sound"/"zero-knowledge-secure".

Shared standing rules (all agents)

  • Out-of-scope discovery → a self-filed GitHub issue, NEVER an inline fix. Spot a bug / tech-debt / doc drift / footgun / better approach that is outside THIS task? Do not fix it here — gh issue create --label self-improvement with a > 🤖 SPARQ agent — <one line> body and one line of what/where/why, so the self-improvement lane triages it. Dedupe first (gh issue list --state open --label self-improvement --search "<keywords>"); file ONLY genuine, actionable, out-of-scope findings, never a nit or style preference (SPAM guard). Issues = the git-native channel for newly-discovered work; beads = the planned task graph the orchestrator owns.
  • Never read agent transcripts / logs. Do NOT Read/cat/grep/ast-grep the /tmp/claude-*/**/tasks/*.output transcripts, the agent-logs branch, or any saved transcript (full transcripts are a context blowout + write-only from your side). Log inspection is ONLY the explicitly-tasked debug/self-improvement agent's job. Transcripts are archived out-of-tree by scripts/save-agent-log.sh; carry a one-line LINK, never the body.

Read the full file on GitHub · 56 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. 6d ago Changed fa8595cc321d
  2. 10d ago First seen · 56 lines · 68 tokens per session scan A 08977d25caa3

Subscribe to this mod's changes

sparq-site is an agent published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,826 once invoked, about $0.0003 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 agents, from other repositories

react18-class-surgeon

Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…

github/awesome-copilot · 81 tokens

react-portfolio-engineer

React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.

notque/vexjoy-agent · 25 tokens

frontend-dev

Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.

vibeeval/vibecosystem · 22 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

pywry-builder

Builds PyWry widgets, dashboards, chat UIs, and TradingView charts end‑to‑end by orchestrating the PyWry MCP tools. Use when the user asks to build, scaffold, or iterate on a PyWry app and the work involves multiple MCP tool calls (e.g. create widget → populate data → add toolbar → wire events → export).

deeleeramone/PyWry · 81 tokens

docs-app-builder

Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…

aayushostwal/nexus · 97 tokens