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.
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWrote 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/frankxai/starlight-intelligence-system/sound-catalog-deplatform-recovery)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-catalog-deplatform-recovery"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-catalog-deplatform-recovery/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.
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sound-catalog-deplatform-recovery"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sound-catalog-deplatform-recovery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00853 |
| Opus 5.5 | $0.00021 | $0.00341 |
| Sonnet 5.5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
sound-catalog-deplatform-recovery 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sound-catalog-deplatform-recovery
Load verticals/sound-intelligence/SKILL.md, agents/starlight-sound-catalog.md, skills/sound-intelligence/catalog-systems.md. Activate Deplatform Recovery Protocol.
Disclaimer (non-waivable)
Copyright disputes and account-suspension events route to music attorney. This protocol coordinates the substrate-side response; it does not adjudicate the dispute.
Process
- Disclaim. Hard hand-off named for legal-side disputes.
- Event triage. Pattern recognition: copyright dispute / account suspension / territorial / AI flag / false-positive / account hack.
- Preservation status check. Master files off-cloud (local + secondary)? Metadata off-platform? Splits documentation off-DDEX?
- Re-release plan. Different distributor / account / territory / alternate-version that resolves dispute.
- Audience communication plan. When to tell list / public / patrons / peers; what to disclose vs. hold.
- Legal hand-off. Music attorney engaged for dispute adjudication.
- Save:
sound-intelligence/catalog/deplatform-<release-slug>-<YYYY-MM-DD>.md.
Output format
# Deplatform Recovery — <Release> — <YYYY-MM-DD>
> **Copyright disputes and account-suspension events route to music attorney. This protocol does not adjudicate.**
## Event
- **Type:** <copyright-dispute / account-suspension / territorial / AI-flag / false-positive / account-hack>
- **Platform:** <Spotify / Apple / etc.>
- **Date detected:** <date>
- **What was removed:** <track(s)>
- **Notice received:** <copy of DSP / claimant notice if available>
## Preservation status
- Master files off-cloud: <yes / GAP — recovery action: ...>
- Metadata off-platform: <yes / GAP>
- Splits documentation off-DDEX: <yes / GAP>
- Source files reconstructable: <yes / no>
## Pattern recognition
- Most likely cause: <hypothesis with reasoning>
- Similar past events: <reference if any>
## Re-release plan
- Alternate distributor: <name>
- Alternate account: <if applicable>
- Alternate version that resolves dispute: <e.g., re-recorded sample / removed sample / cleared sample>
- Target re-release date: <date>
## Audience communication
- **List communication:** <draft message + send timing>
- **Public statement:** <whether / when / what>
- **Patron-only context:** <deeper context for patrons>
- **Peer network:** <reach out for solidarity / reference if pattern recurring>
## Legal hand-off
- Music attorney engaged: <yes — name + date>
- Documentation provided to attorney: <list>
- Next legal step: <attorney-defined>
## Lessons-back-to-system
- What does this event teach the catalog architecture?
- Updates to deplatform-recovery protocol going forward?
**Built on SIP** — SIP v1.1.0 · Sound Intelligence — Catalog · 2026-04-26
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.
- 1mo ago First seen · 85 lines · 52 tokens per session scan A becf43ae083d
sound-catalog-deplatform-recovery is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (11 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 853 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
memories
View and manage learned memories.
mpm-session-resume
Load context from paused session.
forget
Delete specific memories.
learn
Add new learning to memory.
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
agentic-jujutsu
The learning backbone of ACOS. Based on ruvnet's agentic-jujutsu (v2.3.6, MIT), customized for ACOS.