sparq: Agent for Claude Code

.claude/agents/compliance-orchestration.md

compliance-orchestration is an agent for Claude Code from sparq-org/sparq. It costs 44 tokens per session (2,575 once invoked), scanned A, original, MIT.

A runbook for coordinating sparq's certification work across several control frameworks. A runbook is a set of operating instructions; certification frameworks are organized sets of security or compliance requirements.

In plain words
What is it for?
Use it to plan parallel framework work, launch engineering and audit waves, resolve findings, and consolidate the results into a CDMC score.
Why use it?
It explains how to divide the work among engineers and auditors, then combine their findings into one certification assessment.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: 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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../sparq-asvs -b cert-asvs.

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-orchestration.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-orchestration

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sparq-org/sparq/compliance-orchestration"><img src="https://agentmods.dev/badge/agents/sparq-org/sparq/compliance-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,575 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 $0.00044 $0.02575
Opus 5 $0.00022 $0.01288
Sonnet 5 $0.00009 $0.00515
Haiku 4.5 $0.00004 $0.00258

Measured 10d ago against content hash b6d4bd776c16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compliance-orchestration 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 10d 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/compliance-orchestration.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The certification phase is the natural place for fan-out parallelism: each framework's controls + evidence are largely independent. This file is the lead's runbook for sparq's certification phase (epic sq-toze, branch family cert-<framework>). Read alongside compliance-engineer.md + compliance-auditor.md, and research/production-certification-plan.md (the framework set + rationale

  • the grounded gap register).

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.

Why parallel

Sequential would take many days for the 12-framework set (asvs, cis, sbom, ssdf, slsa, openssf, memsafety, iso27001, cra, privacy, cryptoreview, cdmc — matching the git worktree add list below). Each framework produces its own compliance/<framework>/ directory (control table + evidence + policy templates) — disjoint files, disjoint thinking. The auditor pass per framework is independent. Only consolidation + the final CDMC re-score is sequential. Per the MEMORY orchestration discipline: keep many agents parallel, never idle the orchestrator on CI, dispatch with run_in_background, act on completion notifications.

Read the full file on GitHub · 150 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. 10d ago First seen · 150 lines · 44 tokens per session scan A b6d4bd776c16

Subscribe to this mod's changes

compliance-orchestration is an agent published in the GitHub repository sparq-org/sparq (12 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,575 once invoked, about $0.0002 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.