compliance-engineer

compliance-engineer is an agent for Claude Code from sparq-org/sparq. It costs 48 tokens per session (3,011 once invoked), scanned C, original, MIT.

A coding agent for security, privacy, software supply-chain, and certification controls in sparq, a Rust data engine and HTTP server. Certification readiness means producing the controls and evidence needed for high-security use.

In plain words
What is it for?
Use it to implement controls, document evidence, and prepare sparq's Rust, HTTP, cryptography, and WebAssembly components for certification review.
Why use it?
It helps turn security requirements into documented, reviewable evidence instead of leaving compliance decisions scattered across the development process.

Agent for Claude Code

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

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

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/sparq-org/sparq/compliance-engineer
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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sparq-org/sparq/compliance-engineer.svg)](https://agentmods.dev/agents/sparq-org/sparq/compliance-engineer)
Your own site
<a href="https://agentmods.dev/agents/sparq-org/sparq/compliance-engineer"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/compliance-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,011 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00048 $0.03011
Opus 5 $0.00024 $0.01505
Sonnet 5 $0.00010 $0.00602
Haiku 4.5 $0.00005 $0.00301

Measured 6d ago against content hash 82a76fb1baaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

compliance-engineer 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 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.

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.

(`sq-gbp4`) = the re-audit). <!-- [OPUS-4.8] reconciled with post-remediation re-audit (sq-gbp4); see ZK-verdict cross-ref sweep --> Any control claim that presents the ZK/MPC estate as a delivered
.claude/agents/compliance-engineer.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You make sparq certification-ready. sparq is a Rust RDF/SPARQL data-engine library (sparq-core, sparq-engine, sparq-parse, …) + an HTTP server (sparq-server, sparq-serve)

  • a ZK/MPC crypto estate (sparq-zk, sparq-zk-compose, sparq-mpc) + a WASM port (sparq-wasm), intended to be consumed as a dependency in high-security settings. You run at the end of a development cycle, after the conformance + fuzz + Miri lanes are green. You are paired with compliance-auditor, which critically assesses your work; the lead iterates engineer→auditor until the auditor has zero findings.

Read .claude/agents/compliance-orchestration.md for the lead's runbook and your worktree topology, and research/production-certification-plan.md for the full framework set, rationale, and the grounded gap register you are working from.

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 · 142 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 First seen · 142 lines · 48 tokens per session scan C 82a76fb1baaa

Subscribe to this mod's changes

compliance-engineer is an agent published in the GitHub repository sparq-org/sparq (10 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 3,011 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.