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 commands/jonase47/ccpr/p7-release-docsgit clone --depth 1 https://github.com/jonase47/ccprWrote 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/commands/jonase47/ccpr/p7-release-docs)<a href="https://agentmods.dev/commands/jonase47/ccpr/p7-release-docs"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p7-release-docs.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 | $0.00000 | $0.01635 |
| Opus 5 | $0.00000 | $0.00817 |
| Sonnet 5 | $0.00000 | $0.00327 |
| Haiku 4.5 | $0.00000 | $0.00163 |
Grade A, and why
p7-release-docs 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p7-release-docs – Release Notes, User Guide & Privacy Documents
Creates all user-facing documents for the launch: release notes, user guide or onboarding materials, and the legally required mandatory documents (privacy policy, legal notice). These documents must be available before go-live.
Argument: $ARGUMENTS = [Version, e.g. "v1.0.0", "v1.2.0-beta"]
If provided: Use as the version number in release notes and documents. If not provided: Read PROJECT_PLAN.md or DEPLOYMENT_LOG.md and derive the version number. If any context is missing, ask for the version.
Execution
1. Read Context
Read the following files (if available):
- FEATURES.md / BACKLOG.md (what was built in this version?)
- CONCEPT.md (product description and value proposition)
- USER_JOURNEYS.md (personas – who is the guide written for?)
- DSGVO_INITIAL_ASSESSMENT.md (DSGVO (GDPR) requirements for the privacy policy)
- BUSINESS_MODEL.md (pricing, provider information for legal notice)
- UX_CONCEPT.md (screenshots / screen descriptions for the guide)
2. Delegation to Tech Writer Agent (Lead)
Delegate documentation creation to the tech-writer agent:
Create all release documents for version: $ARGUMENTS Context from FEATURES.md, CONCEPT.md, USER_JOURNEYS.md: [Apply implemented features, product description, target audiences]
A. Release Notes (RELEASE_NOTES.md)
- Version and date
- What's new: All new features in plain language (no tech jargon)
- Improvements: What was improved or optimised?
- Bug fixes: Relevant bug fixes (without internal ticket IDs, user-friendly language)
- Breaking changes (if any): What changes for existing users?
- Known limitations: What is not yet perfect, what is being worked on?
- Tone: positive, clear, user-oriented – no marketing exaggerations
B. User Guide / Onboarding Material Create a guide tailored to the target audience from USER_JOURNEYS.md:
- Getting started: How does a new user achieve their first success in 5 minutes?
- Core features explained: The most important features with step-by-step instructions
- Frequently asked questions (FAQ): Answer the 5–10 most likely user questions in advance
- Troubleshooting: What to do when something doesn't work?
- Contact/Support: How do users get help?
- Tone: friendly, direct, tailored to the target persona
C. Privacy Policy (basic structure) Create a legally compliant privacy policy based on DSGVO_INITIAL_ASSESSMENT.md:
- Data controller (name, address, contact)
- What data is collected and why (per processing purpose)
- Legal basis per processing purpose (Art. 6 DSGVO)
- Transfer to third parties (data processors with DPA)
- Retention period per data category
- Data subject rights and how to exercise them
- Right to lodge a complaint with the supervisory authority
- Note: This basic structure must be reviewed by a lawyer.
D. Legal Notice (basic structure) Create a legal notice template according to §5 TMG:
- Provider details (name, address)
- Contact details (email, telephone if applicable)
- Commercial register entry, VAT ID if applicable
- Person responsible for content
- Note: Completeness must be verified.
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.
- 2d ago First seen · 129 lines · 0 tokens per session scan A 9006ed1212a8
p7-release-docs is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,635 tokens. 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 2026-09-03.
Other commands, from other repositories
compliance
Generate compliance-as-code policies with automated evidence. Usage - /mindforge:compliance [--framework soc2|hipaa|pci] [--engine opa|sentinel].
mindforge:fintech
Design fintech payment/ledger architecture. Usage: /mindforge:fintech [service] [--domain payments|ledger|kyc] [--compliance pci|sox].
mindforge:healthcare
Design HIPAA-compliant healthcare system architecture. Usage: /mindforge:healthcare [service] [--standard hipaa|hl7|fhir] [--scope full|audit].
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.
india-checklist
Interactive non-code compliance checklist — business registration, DPO, GST, CERT-In, grievance officer, and more.