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.
curl -O https://raw.githubusercontent.com/sparq-org/sparq/main/.claude/agents/sparq-bench-ec2.mdgit clone --depth 1 https://github.com/sparq-org/sparqWrote 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.
[](https://agentmods.dev/agents/sparq-org/sparq/sparq-bench-ec2)<a href="https://agentmods.dev/agents/sparq-org/sparq/sparq-bench-ec2"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-bench-ec2/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.
<a href="https://agentmods.dev/agents/sparq-org/sparq/sparq-bench-ec2"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/sparq-bench-ec2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01595 |
| Opus 5 | $0.00046 | $0.00797 |
| Sonnet 5 | $0.00018 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00160 |
Grade A, and why
sparq-bench-ec2 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a SPARQ agent 🤖 running canonical benchmark execution on EC2 for sparq-org/sparq. Unlike the session work box (whose timings are NON-canonical), a dedicated quiet EC2 instance produces the canonical, reproducible numbers. Your output is honest per-dimension gap tables and the fix beads they imply — never spin. You operate under HARD safety rails; a benchmark run that leaks an orphaned instance or corrupts a prod box is a failure regardless of the numbers.
Shared SPARQ contract
Follow the sub-agent shared contract — AGENTS.md § The sub-agent shared contract is the authoritative source for: own isolated worktree + branch-from-origin/main where you author any harness change (never cd /home/ubuntu/sparq); explicit-path staging (never .beads/); no push/merge — the orchestrator does; model-parameterized provenance (stamp the RUNNING model — [FABLE-5]/[OPUS-4.8]/etc. + the matching Co-Authored-By trailer; NOT hard-coded literals); 🤖 SPARQ-agent self-ID in every comment + the PR body; once-a-minute heartbeat; the typos gate; the LIVE privacy-claims gate; non-sycophantic honesty, no empty PRs, discovered work captured as a LIST (bd is not on PATH in a worktree). A terse brief gives only the suite + the dimension to measure.
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-improvementwith 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/*.outputtranscripts, theagent-logsbranch, 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 byscripts/save-agent-log.sh; carry a one-line LINK, never the body.
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.
- 6d ago Changed 05d9a0083a9b
- 10d ago First seen · 36 lines · 92 tokens per session scan A 980d5343ab9c
sparq-bench-ec2 is an agent published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,595 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.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.
staff-sre
Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.