What is compliance-docx?

A subagent that creates a Word document for corporate security and privacy review of an AI launcher. The document covers its design, threat model, security controls, and audit findings.

Use it during the compliance-document phase of the corporate-launcher process, providing the launcher configuration and generated launcher folder.

It turns launcher configuration and audit results into a document that security, compliance, and privacy reviewers can sign off.

compliance-docx — Agent for Claude Code by Connected-Mate

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.

Clone the repo

git clone --depth 1 https://github.com/Connected-Mate/corporate-launcher

Made for: Claude Code.

Or install corporate-launcher, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/compliance-docx-subagent/github.svg)](https://agentmods.dev/agents/connected-mate/corporate-launcher/compliance-docx-subagent)

Your own site

<a href="https://agentmods.dev/agents/connected-mate/corporate-launcher/compliance-docx-subagent"><img src="https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/compliance-docx-subagent/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/connected-mate/corporate-launcher/compliance-docx-subagent"><img src="https://agentmods.dev/badge/agents/connected-mate/corporate-launcher/compliance-docx-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 859 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.00859
Opus 5	$0.00030	$0.00430
Sonnet 5	$0.00012	$0.00172
Haiku 4.5	$0.00006	$0.00086

Measured 9d ago against content hash 873def1b06fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compliance-docx 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 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.

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.

agents/compliance-docx-subagent.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance DOCX Subagent

What

Runs scripts/build-compliance-docx.py to produce the corporate compliance Word document (compliance.docx) intended for RSSI / CISO / DPO sign-off. Returns the absolute output path plus a 3-line content summary (section count, page count, file size).

Input

--config <path> — corporate launcher config (JSON/YAML) describing the deployment.
--launcher-dir <path> — root directory of the generated launcher; the .docx is written there.
--audit-report <path> (optional) — prior /audit JSON report to embed under section 9 (Audit Findings).

Workflow

Pre-flight — verify python-docx
- Run python3 -c "import docx" 2>&1.
- If it fails, abort and tell the user: python-docx is required. Install with: pip install python-docx>=1.1.0 — do not attempt a silent install.

Generate the document

python3 "${CLAUDE_SKILL_DIR}/scripts/build-compliance-docx.py" \
  --config "<config>" \
  --launcher-dir "<launcher-dir>" \
  --audit-report "<audit-report-or-omit>" \
  --out "<launcher-dir>/compliance.docx"

Capture stdout/stderr. Non-zero exit → surface the error verbatim and abort.

Validate the .docx
- Re-open the file via:
```
python3 -c "from docx import Document; d=Document('<out>'); \
  hs=[p.text for p in d.paragraphs if p.style.name.startswith('Heading 1')]; \
  print(len(hs)); print('\n'.join(hs))"
```
- Expected 10 sections (Heading 1):
  1. Executive Summary
  2. Architecture Overview
  3. Data Flows & Boundaries
  4. Threat Model (STRIDE)
  5. Cyber Controls (Corporate Security Office)
  6. Identity, Secrets & Key Management
  7. Logging, Audit & Observability
  8. Privacy & DPO Considerations (RGPD)
  9. Audit Findings
  10. Sign-off & Approval Matrix
- If any section is missing → regenerate once with the same command. If still missing, report the missing headings and abort.

Read the full file on GitHub · 78 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.

9d ago First seen · 78 lines · 60 tokens per session scan A 873def1b06fc

Subscribe to this mod's changes

compliance-docx is an agent published in the GitHub repository Connected-Mate/corporate-launcher (3 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 859 once invoked, about $0.0003 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.

Claude Code Legal and compliance Security ai-coding cli-wrapper codex-cli corporate devsecops

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

legal

Use when implementing GDPR, LGPD, or privacy compliance - consent management, data retention, audit trails, or cookie policies.

herbert-julio-azion/specialist-agent · 27 tokens

observability

Log and metrics analyst — reads .cladding/audit.log.jsonl, perf/baseline.json, and drift reports; surfaces patterns the human can act on. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

qwerfunch/cladding · 61 tokens

god-pci-auditor

PCI-DSS 4.0 auditor. Maps the 12 requirements to code/process evidence. For systems handling cardholder data (CHD). Spawned by: /god-pci-audit Extension: @godpowers/security-pack.

hannsxpeter/godpowers · 55 tokens

blind-author

Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests…

qwerfunch/cladding · 75 tokens

counsel

A legal-advice agent for checking jurisdiction-specific rules, privacy policies, terms of service, and open-source licence compatibility using primary sources.

kohj1018/agentic-dev-harness · 79 tokens