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 prenats/claude-imagine --skill image-suggestgit clone --depth 1 https://github.com/prenats/claude-imagineWrote 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/prenats/claude-imagine/image-suggest)<a href="https://agentmods.dev/skills/prenats/claude-imagine/image-suggest"><img src="https://agentmods.dev/badge/skills/prenats/claude-imagine/image-suggest/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/prenats/claude-imagine/image-suggest"><img src="https://agentmods.dev/badge/skills/prenats/claude-imagine/image-suggest.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 | $0.00032 | $0.01951 |
| Opus 5.5 | $0.00013 | $0.00780 |
| Sonnet 5.5 | $0.00006 | $0.00390 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade A, and why
image-suggest 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 2mo 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/image-suggest — Project Image Planning
Analyze a project and produce a prioritized, context-aware set of image recommendations. Optionally generate all images in one go.
When to Activate
User-invoked only — do NOT auto-trigger during coding flow. Use /claude-imagine:image-generate inline instead.
Activate ONLY when the user explicitly:
- Asks "what images do I need?" or wants image recommendations
- Requests a visual asset plan or audit
- Runs
/claude-imagine:image-suggestdirectly - Wants to see all needed images before starting a project
Usage
/image-suggest
/image-suggest a SaaS landing page for a project management tool
/image-suggest a construction equipment reseller website
/image-suggest --generate
Argument Parsing
Parse $ARGUMENTS for:
- Project description — free-text description (optional; scans project files if omitted)
--generate— skip confirmation, generate all suggestions immediately--output-dir PATH— base directory for output files. Default:generated/--max NUMBER— maximum suggestions. Default: 6
Workflow
┌─────────────────────────────────────────────────┐
│ 1. UNDERSTAND PROJECT │
│ Scan files or use provided description │
│ Classify into project archetype │
├─────────────────────────────────────────────────┤
│ 2. GENERATE SUGGESTIONS (4-8 images) │
│ Project-specific descriptions, not generic │
│ Priority: must-have → important → nice │
├─────────────────────────────────────────────────┤
│ 3. DISPLAY RECOMMENDATIONS │
│ Formatted list with rationale per image │
│ Ask: "Generate all? (yes / select / no)" │
├─────────────────────────────────────────────────┤
│ 4. GENERATE SELECTED IMAGES │
│ Full /image-generate prompt engineering │
│ per image (150-250 word prompts) │
├─────────────────────────────────────────────────┤
│ 5. SUMMARY REPORT │
│ Paths, dimensions, seeds for reproducibility │
└─────────────────────────────────────────────────┘
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.
- 2mo ago First seen · 231 lines · 32 tokens per session scan A 8cc23cfbc218
image-suggest is a skill published in the GitHub repository prenats/claude-imagine (1 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,951 once invoked, about $0.0001 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 2026-08-31.
image-suggest compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| image-suggestprenats/claude-imagine | Skill | 1 | 4mo ago | MIT | A | 32 | Claude Code |
| example-feature-generatorqf-studio/navigator | Skill | 355 | 5d ago | MIT | A | 33 | Claude Code |
| authentication-patternstravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 28 | Claude Code, Codex |
| agent-flutter-developertravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 74 | Claude Code |
| content-repurposertravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| electron-desktoptravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 38 | Claude Code, Codex |
| impact-report-writertravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 43 | Claude Code, Codex |