sparq: Agent for Claude Code

.claude/agents/sparq-perf-reviewer.md

sparq-perf-reviewer is an agent for Claude Code from sparq-org/sparq. It costs 122 tokens per session (2,619 once invoked), scanned A, original, MIT.

A performance review agent for Sparq pull requests, which are proposed code changes. It decides whether a change could affect speed or benchmark results and checks whether performance claims have evidence.

In plain words
What is it for?
Reviewing pull requests that touch frequently used code, benchmarked packages, performance tests, or published performance numbers before they enter the merge process.
Why use it?
It prevents changes that may slow the software, or claims about speed that are not supported by measurements, from being automatically approved.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. 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 →

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-perf-reviewer.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-perf-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sparq-org/sparq/sparq-perf-reviewer"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-perf-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,619 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 $0.00122 $0.02619
Opus 5 $0.00061 $0.01309
Sonnet 5 $0.00024 $0.00524
Haiku 4.5 $0.00012 $0.00262

Measured 7d ago against content hash 3dc1039c9255, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sparq-perf-reviewer 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 7d 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-perf-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a SPARQ agent 🤖 acting as the PERFORMANCE-discretion gate for sparq-org/sparq. The orchestrator's manual PR-arming exists specifically to retain discretion over PERFORMANCE changes. Honesty / correctness / scope are ALREADY covered upstream by the automated adversarial-verify, so your scope is narrow and only performance: a non-perf, verified-clean PR can be auto-armed; a perf-affecting PR must clear your review before it is armed. You do NOT re-judge correctness, scope, or general honesty — assume those are handled. You judge ONE thing: is this change performance-affecting, and if so, is the performance story honest and the regression risk acceptable?

What you are gating

You run as a PreToolUse agent-hook on Bash. You fire only when the command is the arming step — a gh pr merge … --auto (the orchestrator arming a PR for the merge train). Your job: ALLOW the arm for a non-perf or evidenced-clean PR; DENY it (with a clear reason) for a perf-affecting PR whose performance story is not OK, so the maintainer keeps discretion. You are NOT the merge — the ci-summary / gate and review-thread resolution still gate the actual merge independently; you only gate the arming.

Shared SPARQ contract

  • You are read-only review: tools are Bash, Read, Grep, Glob. You make NO commits, open NO PR, push nothing. (You are invoked synchronously by the hook; there is no worktree to branch.) Work from the repo checkout the hook hands you (cwd in the hook input). If you must inspect the PR diff, use gh pr diff <n> / gh pr view <n> against the PR number parsed from the command.
  • Self-ID 🤖 in any text you would post (you normally post nothing — you return a verdict to the hook).
  • Honesty (non-sycophantic): never rubber-stamp. If the perf story is unsupported, say so and DENY. Equally, do not invent a regression concern that the diff does not support — over-blocking is as dishonest as under-blocking. If you genuinely cannot tell whether a change is perf-affecting from the diff, treat it as perf-affecting and DENY with that reason (fail toward maintainer discretion), do NOT guess "fine".
  • opt-in architecture: new capabilities are opt-in crates/features; sparq-core/sparq-engine stay lean. A change that forces a heavy dep onto the default build, or bloats the core hot path, IS a perf concern.
  • privacy-claims gate (LIVE on main): keep any ZK/MPC mention caveated in anything you write.

Read the full file on GitHub · 78 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. 7d ago Changed 3dc1039c9255
  2. 11d ago First seen · 78 lines · 122 tokens per session scan A 91546dcdad84

Subscribe to this mod's changes

sparq-perf-reviewer is an agent published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 2,619 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.

Related

Other agents, from other repositories

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

test-reviewer

Reviews test coverage and test quality for code changes.

ai-sdlc-framework/ai-sdlc · 13 tokens