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/sip-attest-audio)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sip-attest-audio"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sip-attest-audio/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/sip-attest-audio"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sip-attest-audio.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 | $0.00057 | $0.01760 |
| Opus 5 | $0.00028 | $0.00880 |
| Sonnet 5 | $0.00011 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
sip-attest-audio 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 12d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sip-attest-audio
Load SIP.md, docs/attested-modalities.md, and ATTESTATIONS.md. Attach Starlight Intelligence Protocol attestation to an audio artifact (track, voice-over, podcast episode, soundscape).
Artifact
$ARGUMENTS
Process
-
Validate input.
- Parse
<audio-file-path>from$ARGUMENTS. Resolve to absolute path. - Verify file exists. If not, emit:
Cannot attest — file not found: <path>.Halt. - Verify extension in {
.mp3,.wav,.flac,.ogg,.m4a}. If not, emit:Cannot attest — not an audio container. Supported: mp3, wav, flac, ogg, m4a.Halt. - Parse optional flags
--tool(defaultgeneric) and--canon(defaultnone).
- Parse
-
Scan for real composition. Refuse decorative attestation — same rule as
/sip-attestfor text.- Check for tool-reported metadata (e.g., Suno embeds prompt + model ID in ID3; ElevenLabs sets generator tags).
- Check for prompt provenance in a co-located
<filename>.prompt.txtor<filename>.jsonif present. - Check for canon references — if
--canon hz, verify a Hz grounding declaration is present (Hz values used in the track, stated in prompt or metadata). If--canon arcanea, verify canonical element references (Guardian names, Vel'Tara sites) in prompt or metadata. - If no composition signals found AND
--tool genericAND--canon none, emit:Cannot attest — no SIP composition detected. Attestation would be decorative, which corrodes the protocol.Halt. - Tool hint alone is not composition — tool + prompt + (optional) canon together are.
-
Compute composition hash.
- Emit a
sha256sum <audio-file-path>Bash command. Capture the hash. - This hash is what the attestation binds to. Tampering with the audio payload breaks the bind.
- Emit a
-
Generate SIP attestation block. Audio-specific fields extend the base
/sip-attestformat:- Standard fields: substrate version, layers used, verticals, canon, nodes, generated timestamp.
- Audio-specific fields:
duration_seconds,sample_rate_hz,channels,tool,tool_version(if reported),prompt_hash(sha256 of the prompt text if provided; not the prompt itself, to preserve prompt IP),canon_refs(list of canon elements if canon composed),payload_sha256(from step 3). - If
--canon hz, addhz_valuesfield listing the Hz values claimed (e.g.,[528, 432]).
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.
- 12d ago First seen · 122 lines · 57 tokens per session scan A 942f9c987212
sip-attest-audio is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,760 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.
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.
agentos-status
Show AgentOS system status — agents, workers, health.