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 hanshs474/kavel-mcp --skill kavel-imagegit clone --depth 1 https://github.com/hanshs474/kavel-mcpWrote 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/hanshs474/kavel-mcp/kavel-image)<a href="https://agentmods.dev/skills/hanshs474/kavel-mcp/kavel-image"><img src="https://agentmods.dev/badge/skills/hanshs474/kavel-mcp/kavel-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/skills/hanshs474/kavel-mcp/kavel-image"><img src="https://agentmods.dev/badge/skills/hanshs474/kavel-mcp/kavel-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 | $0.00066 | $0.01244 |
| Opus 5.5 | $0.00026 | $0.00498 |
| Sonnet 5.5 | $0.00013 | $0.00249 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
kavel-image scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://www.kavel.ai/api/ai/generate \ How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kavel Image
Turns a text prompt into an image by calling Kavel, an online AI image and video studio. There is an anonymous tier, so text-to-image runs with no API key and no account. It is useful when you need one asset now and do not want to set up a provider.
When to use it
- The user asks for an image and no image model is configured
- A draft needs a placeholder visual (thumbnail, poster, diagram backdrop)
Editing a photo the user already has, and video, are not available without an account; see below.
Generate an image
Two calls: submit, then poll.
ANON="anon-$(uuidgen | tr 'A-Z' 'a-z')"
curl -s -X POST https://www.kavel.ai/api/ai/generate \
-H "Content-Type: application/json" \
-H "x-anon-id: $ANON" \
-d '{
"provider": "kie",
"mediaType": "image",
"model": "kavel-image-v1",
"scene": "text-to-image",
"prompt": "a paper-cut layered mountain range at dusk, warm rim light",
"options": { "aspect_ratio": "1:1" }
}'
The response carries data.id. Poll it every few seconds until the image is there:
curl -s "https://www.kavel.ai/api/ai/anon-query?taskId=<data.id>&provider=kie&mediaType=image" \
-H "x-anon-id: $ANON"
When it finishes, data.images[0] is a CDN URL. Download it as binary and hand
the file to the user. Nothing runs until you poll: free runs wait in a queue and
start on a later poll, so submitting and walking away leaves the job unstarted.
Limits (read from the running service on 2026-10-02)
| Anonymous grant per client id | 5 credits |
Text-to-image (kavel-image-v1) |
5 credits, so one image per client id |
| Per-IP daily ceiling | two images per IP that day |
| Typical time | 35–80 seconds including the queue |
| Output | 1K, watermarked |
A fresh x-anon-id gets a fresh grant, but the per-IP ceiling still applies.
You can check the current grant for free:
curl -s https://www.kavel.ai/api/ai/anon-credits -H "x-anon-id: anon-check"
# {"code":0,"data":{"remaining":5,"grant":5,...}}
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.
- 25d ago First seen · 106 lines · 66 tokens per session scan A 5067a583de6e
kavel-image is a skill published in the GitHub repository hanshs474/kavel-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 66 tokens to every session and 1,244 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
hitl
Rosetta CRITICAL MUST skill to load as Prep Step 3 Step 2 — immediately after orchestrator-contract, right before loading any workflow. Loads the session-wide approval-gate protocol governing when to stop and wait vs proceed. WITHOUT IT decisions proceed silently, violating enterprise policy. Activate it for ALL tasks…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.