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/deapi-ai/claude-code-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/commands/deapi-ai/claude-code-skills/generate-image)<a href="https://agentmods.dev/commands/deapi-ai/claude-code-skills/generate-image"><img src="https://agentmods.dev/badge/commands/deapi-ai/claude-code-skills/generate-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/deapi-ai/claude-code-skills/generate-image"><img src="https://agentmods.dev/badge/commands/deapi-ai/claude-code-skills/generate-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 | $0.00020 | $0.00785 |
| Opus 5.5 | $0.00008 | $0.00314 |
| Sonnet 5.5 | $0.00004 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
generate-image 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 1mo 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.
curl -s -X POST "https://api.deapi.ai/api/v1/client/txt2img" \ This is a copy
100% identical to generate-image — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generation via deAPI
Generate image from prompt: $ARGUMENTS
Step 1: Parse arguments
Extract from $ARGUMENTS:
prompt: The text description (required)--model:klein(default, recommended),flux(higher max resolution), orturbo(fastest)--size:512,768, or1024(default: 1024). Klein supports up to 1536.
Step 2: Send request
curl -s -X POST "https://api.deapi.ai/api/v1/client/txt2img" \
-H "Authorization: Bearer $DEAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "{prompt}",
"model": "{model_name}",
"width": {size},
"height": {size},
"steps": {steps},
"seed": {random_seed}
}'
Model mapping:
| User flag | API model name | Steps | Max size | Info |
|---|---|---|---|---|
klein (default) |
Flux_2_Klein_4B_BF16 |
4 (fixed) | 1536 | Recommended, txt2img + img2img, multi-image |
flux |
Flux1schnell |
4-10 (default: 4) | 2048 | Higher max resolution |
turbo |
ZImageTurbo_INT8 |
4-10 (default: 4) | 1024 | Fastest |
Klein model limits:
- Resolution: 256-1536px (step: 16)
- Steps: 4 (fixed)
- Guidance: not supported (parameter ignored)
Important: Generate a random seed (0-999999) for each request.
Note: Klein does not support guidance parameter - omit it or it will be ignored.
Step 3: Poll status (feedback loop)
Extract request_id from response, then poll every 10 seconds:
curl -s "https://api.deapi.ai/api/v1/client/request-status/{request_id}" \
-H "Authorization: Bearer $DEAPI_API_KEY"
Status handling:
processing→ wait 10s, poll againdone→ proceed to Step 4failed→ report error message to user, STOP
Step 4: Fetch and present result
When status = "done":
- Get image URL from
result_url - Display/download the generated image
- Show the image to the user
Step 5: Offer follow-up
Ask user:
- "Would you like variations with a modified prompt?"
- "Should I upscale this image?"
- "Would you like to transform this with additional images?" (Klein supports up to 3 input images in img2img)
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.
- 1mo ago First seen · 87 lines · 20 tokens per session scan A 299e53ef9feb
generate-image is a command published in the GitHub repository deapi-ai/claude-code-skills (21 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 785 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to generate-image, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
learn
Capture what the user changed in a draft the skill wrote, so the loop can learn from it. Every rewrite, cut, or addition is evidence; this command turns it into ledger records that /humanise improve mines for rule-change candidates.
tray-referencia-api
Referência rápida de todos os endpoints da API da Tray, aceita nome do recurso como filtro.
fingerprint
(Re)generate the user's voice fingerprint from their corpus. Run after adding profile/sample-.md samples.
perf-investigate
Drive an iOS performance or memory-leak investigation on using Memory Graph + Time Profiler. Enforce data-before-architecture and stacked PRs.
code-review
Review code quality applying DRY, SOLID, naming, and formatting standards.
create-pr-from-staged-changes
You are helping to create a pull request following the iOS team's standard template.