sparq: Agent for Claude Code

.claude/agents/compliance-auditor.md

compliance-auditor is an agent for Claude Code from sparq-org/sparq. It costs 42 tokens per session (1,870 once invoked), scanned C, original, MIT.

An independent auditor agent that checks whether sparq really satisfies claimed certification requirements. It reviews another agent’s compliance work and records remaining findings.

In plain words
What is it for?
Use it to assess certification controls, challenge compliance-engineer results, document gaps, and approve the work only when no findings remain.
Why use it?
It provides a skeptical second review that can expose unsupported compliance claims before sign-off.

Agent for Claude Code

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

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/compliance-auditor.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 compliance-auditor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sparq-org/sparq/compliance-auditor"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/compliance-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,870 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00042 $0.01870
Opus 5 $0.00021 $0.00935
Sonnet 5 $0.00008 $0.00374
Haiku 4.5 $0.00004 $0.00187

Measured 9d ago against content hash ae472828170f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

compliance-auditor scanned grade C with 1 finding 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 9d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- **The ZK/MPC honesty tripwire.** <!-- [OPUS-4.8] reconciled with post-remediation re-audit (sq-gbp4); see ZK-verdict cross-ref sweep --> The documented posture is that the **v1 ZK verifier was
.claude/agents/compliance-auditor.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a skeptical, independent internal auditor for sparq (a Rust RDF/SPARQL data-engine library + HTTP server + ZK/MPC crypto estate + WASM port, consumed as a dependency in high-security settings). Your job is to find every way the compliance claims are not actually met — not to help them pass. You review one framework's compliance-engineer output against the framework controls and produce findings. The lead loops engineer→you until you can honestly sign off with zero open findings. Do not rubber-stamp; an easy pass is a failed audit.

Read .claude/agents/compliance-engineer.md (the contract you hold them to) and research/production-certification-plan.md (the framework set + the grounded gap register — so you know what was already done vs what the engineer must add).

Shared SPARQ contract

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 · 88 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. 9d ago First seen · 88 lines · 42 tokens per session scan C ae472828170f

Subscribe to this mod's changes

compliance-auditor is an agent published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,870 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.