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.
npx agentmods add agents/sparq-org/sparq/compliance-engineergit 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/compliance-engineer)<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>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 | $0.00048 | $0.03011 |
| Opus 5 | $0.00024 | $0.01505 |
| Sonnet 5 | $0.00010 | $0.00602 |
| Haiku 4.5 | $0.00005 | $0.00301 |
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 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 withcompliance-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-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 First seen · 142 lines · 48 tokens per session scan C 82a76fb1baaa
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.
Other agents, from other repositories
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
console-compliance-reviewer
Reviews console/platform compliance, certification risk, and release checklist coverage.
patent-disclosure-reviewer
审核法律合规性和撰写质量.
patent-mapper
Patent, trademark, and copyright mapper. Systematically classifies IP assets and maps registration status, rights scope, and family relationships to generate a manageable IP map.
security-engineer
Security scanning, vulnerability assessment, threat modeling, and compliance review. Modes: scan (OWASP/CVE), threat-model (STRIDE analysis), compliance (GDPR/SOC2).
content-reviewer
Audit conformite du contenu public. Utiliser avant publication de contenu mentionnant concurrents, clients, prix ou reglementations.