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 skills add calesthio/generative-media-skills --skill luma-photongit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/skills/calesthio/generative-media-skills/luma-photon)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/luma-photon"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/luma-photon/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/skills/calesthio/generative-media-skills/luma-photon"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/luma-photon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 34 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 720 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 24 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 161 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00084 | $0.09614 |
| Opus 5 | $0.00042 | $0.04807 |
| Sonnet 5 | $0.00017 | $0.01923 |
| Haiku 4.5 | $0.00008 | $0.00961 |
Grade A, and why
luma-photon scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.error How it starts
The opening of the file, as written. The whole thing — 756 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Luma Photon production guide
Use this skill for the legacy-path Luma API image surface backed by photon-1 and photon-flash-1. Keep it separate from Ray video generation, newer UNI image workflows, Luma Agents, the consumer app, ComfyUI wrappers, and hosted third-party gateways. The string dream-machine remains in the documented Photon REST path even though Luma's current brand guidance calls that terminology retired.
All volatile facts below were verified against first-party sources on 2026-07-09. Recheck the API reference, billing dashboard, rate-limit page, and governing agreement immediately before production commitments.
Choose Photon deliberately
The documented image model IDs are:
photon-1— the default Photon model. Luma positions it for higher-fidelity generation.photon-flash-1— the faster, lower-cost iteration model.
Treat those descriptions as provider positioning, not independent quality findings. Run a fixed brief-and-reference bake-off using the intended deliverable, then compare prompt adherence, source fidelity, text, anatomy, material continuity, latency, rejection rate, and actual account charge. Use Flash for broad exploration when it meets the bar; promote only finalists to Photon when measured quality justifies the cost.
Do not send Photon work to /generations/video, Ray models, Luma Agents, a consumer-session endpoint, or an OpenAI-compatible gateway. The first-party Photon create route is:
POST https://api.lumalabs.ai/dream-machine/v1/generations/image
Authorization: Bearer $LUMAAI_API_KEY
Content-Type: application/json
The shared management routes are:
GET /dream-machine/v1/generations/{id}
GET /dream-machine/v1/generations?limit=100&offset=0
DELETE /dream-machine/v1/generations/{id}
GET /dream-machine/v1/credits
The official Python package is lumaai; its image create surface is client.generations.image.create(...), while polling uses client.generations.get(id=...). Direct REST is used in the complete example so timeout, redirect, byte, decode, and persistence behavior stays explicit.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 756 lines · 84 tokens per session scan A 11e91b8a82a1
luma-photon is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 9,614 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…