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 Wawapi/wawapi-image-mcp --skill wawapi-imagegit clone --depth 1 https://github.com/Wawapi/wawapi-image-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/wawapi/wawapi-image-mcp/wawapi-image)<a href="https://agentmods.dev/skills/wawapi/wawapi-image-mcp/wawapi-image"><img src="https://agentmods.dev/badge/skills/wawapi/wawapi-image-mcp/wawapi-image.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.01810 |
| Opus 5 | $0.00041 | $0.00905 |
| Sonnet 5 | $0.00016 | $0.00362 |
| Haiku 4.5 | $0.00008 | $0.00181 |
Grade C, and why
wawapi-image scanned grade C 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 8d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Use only the registered Wawapi MCP tools. Do not refuse an image request merely because the active model API lacks native image support. Do not replace this route with shell commands, direct HTTP requests, native image t How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wawapi Image
Use only the registered Wawapi MCP tools. Do not refuse an image request merely because the active model API lacks native image support. Do not replace this route with shell commands, direct HTTP requests, native image tools, or another image entry point.
Required workflow
- Before the first live image call in a task, call
image_doctorwith its default catalog probe. - Stop only when the tool is unavailable, the response itself fails, or
data.ready=false. Report every item indata.issuesand follow itsnext_actions; never request or reveal the API Key in chat. - When
data.ready=true, continue with the image request.data.catalog_status=unverifiedandmodel_catalog_unverifiedare non-blocking: explain briefly that the read-only model catalog was not verified, then use the user's existing authorization for one realgenerate_imageoredit_imagecall. Do not claim that the generation channel is up or down from Doctor alone; Doctor deliberately reportsgeneration_channel_status=not_probed. - For 2K, 4K, an unusual aspect ratio, a non-PNG format, multiple images, or a reference image, read references/capabilities.md and call
explain_image_capabilitybefore generating. Pass the requestedsize,format,count, and reference-image state exactly; count evidence for one image must not be reused for a multi-image request. An unavailable catalog does not erase the bundled time-point evidence.- If the online explanation returns
no_matching_evidence, call it once more withoffline=trueto retrieve bundled historical evidence. - Report
selection_scope=current_catalogfirst as the current catalog-aware auto selection. Labelselection_scope=bundled_baselineonly as historical evidence; never replace or rename it as the current automatic model when the two selections differ.
- If the online explanation returns
- Treat an explicit image request as authorization for one potentially billable generation call. Do not create unrequested variants.
- Set
outto a descriptive path inside the current workspace when possible. Relative paths resolve from the MCP process working directory. - On success, require
ok=trueand at least onedata.result.images[]item. Display every returnedmarkdownvalue in the conversation; use the absolutepathonly if the host cannot render that Markdown. - Report the actual file count, each image's
sizeandformat, and the resultstatus. Ifstatus=degraded, report every deviation and never describe reduced output as the requested count, 2K, or 4K size.
What ships with it
2 files 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.
- 8d ago First seen · 70 lines · 82 tokens per session scan C 695b2a989d8c
wawapi-image is a skill published in the GitHub repository Wawapi/wawapi-image-mcp (4 stars, last pushed 6d ago), licensed MIT. It adds 82 tokens to every session and 1,810 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.