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-image)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/sip-attest-image"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sip-attest-image/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-image"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/sip-attest-image.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 | $0.00055 | $0.01865 |
| Opus 5 | $0.00028 | $0.00932 |
| Sonnet 5 | $0.00011 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
sip-attest-image 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 6d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sip-attest-image
Load SIP.md, docs/attested-modalities.md, and ATTESTATIONS.md. Attach Starlight Intelligence Protocol attestation to an image artifact (book cover, character art, infographic, world-map render, brand drop).
Artifact
$ARGUMENTS
Process
-
Validate input.
- Parse
<image-file-path>from$ARGUMENTS. Resolve to absolute path. - Verify file exists. If not, emit:
Cannot attest — file not found: <path>.Halt. - Verify extension in {
.png,.jpg,.jpeg,.webp,.gif,.tiff}. If not, emit:Cannot attest — not an image container. Supported: png, jpg, jpeg, webp, gif, tiff.Halt. - Parse optional flags
--tool(defaultgeneric),--canon(defaultnone),--watermark(default off).
- Parse
-
Scan for real composition. Refuse decorative attestation — same rule as
/sip-attestfor text.- Check for tool-reported EXIF (e.g., Imagen and Nano Banana write generator tags; Midjourney and DALL-E often embed model/version).
- Check for prompt provenance in a co-located
<filename>.prompt.txtor<filename>.jsonif present. - If
--canon arcanea, verify canonical element references (Guardian names, Vel'Tara sites, Hz-bound visual motifs) in prompt 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.
-
Compute composition hash.
- Emit a
sha256sum <image-file-path>Bash command. Capture the hash. - Hash binds to the exact pixel payload. Any re-compression breaks the bind (expected behavior — the re-encoded image is a derivative and must be re-attested).
- Emit a
-
Generate SIP attestation block. Image-specific fields extend the base format:
- Standard fields: substrate version, layers used, verticals, canon, nodes, generated timestamp.
- Image-specific fields:
width_px,height_px,format(PNG/JPEG/WEBP/...),color_space(sRGB/P3/...),tool,tool_version(if reported),prompt_hash(sha256 of prompt text if provided),canon_refs(list if canon composed),payload_sha256(from step 3).
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.
- 6d ago First seen · 144 lines · 55 tokens per session scan A d2366e19ead0
sip-attest-image is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,865 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 2026-09-03.
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.