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 AiAi-Mastermind/aiai-mastermind-tools-and-skills --skill image-brandgit clone --depth 1 https://github.com/AiAi-Mastermind/aiai-mastermind-tools-and-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/aiai-mastermind/aiai-mastermind-tools-and-skills/image-brand)<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/image-brand"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/image-brand/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/aiai-mastermind/aiai-mastermind-tools-and-skills/image-brand"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/image-brand.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 | $0.00077 | $0.00971 |
| Opus 5 | $0.00039 | $0.00485 |
| Sonnet 5 | $0.00015 | $0.00194 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
image-brand 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image and Brand
Codex is the designer on this team, and you are the creative director. Codex only does great work when the brief is exact: precise hex codes, real reference photos, one named emotion, and the exact text that goes on the image. This skill is that brief, every time.
Hard rules (read before every generation)
- Only the owner appears in generated images. The only face source is
skills/image-brand/face-reference/. No staff, no clients, no invented people presented as real. If a concept needs a crowd, use silhouettes, illustration, or objects instead. - Exact brand colors only. Read the hex codes from the MY BRAND section of
brain/My_Agency_Context.mdand pass them verbatim into the prompt. "Blue-ish" is not a brand. - Every visual is emotional and eye-catching first. A technically correct but flat image fails. Name the one emotion before you write the prompt.
- Text on image is the hook, 5 to 10 words, readable on a phone in one second.
Step 1: Assemble the brief
From the lane skill's handoff and the brain, collect:
- Concept: one sentence, what the image shows
- Emotion: one word (pride, relief, suspense, laughing-with)
- Text on image: the exact hook words
- Brand: hex codes, fonts or font feel, and visual style notes from MY BRAND
- Owner in frame? If yes, pick the 2 or 3 clearest face-reference photos for the pose and angle needed
- Reference notes: for newsjacking, the recognizable specifics of the real event (jersey colors, setting) gathered by web search
- Size: 1080x1080 square or 1080x1350 portrait for Instagram feed; one image per carousel slide
Step 2: Generate through Codex CLI
Call Codex non-interactively with the face references attached as image inputs and a complete prompt. Pattern:
codex exec \
-i "skills/image-brand/face-reference/<photo-1>.jpg" \
-i "skills/image-brand/face-reference/<photo-2>.jpg" \
"Use your built-in image generation tool. Generate a 1080x1350 social media
image. The person in the attached reference photos is the agency owner;
match their face and likeness exactly, but not their clothing. Scene:
[concept]. Emotion: [emotion]. Text on the image, large and high-contrast:
'[hook text]'. Brand colors, use these exact hex values: [#......, #......].
Style: [MY BRAND style notes]. Footer strip: [Agency Name] | [contact].
Save the result to output/drafts/<post-folder>/image-1.png"
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.
- 12d ago First seen · 68 lines · 77 tokens per session scan A b3375f224cf3
image-brand is a skill published in the GitHub repository AiAi-Mastermind/aiai-mastermind-tools-and-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 971 once invoked, about $0.0004 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 skills, from other repositories
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.