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 tranfu-labs/tranfu-skills --skill compress-imagegit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/compress-image)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/compress-image"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/compress-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/tranfu-labs/tranfu-skills/compress-image"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/compress-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 | $0.00107 | $0.01249 |
| Opus 5 | $0.00053 | $0.00624 |
| Sonnet 5 | $0.00021 | $0.00250 |
| Haiku 4.5 | $0.00011 | $0.00125 |
Grade A, and why
compress-image 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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compress Image
Compress one local image or a local directory with the bundled deterministic CLI. MUST keep source files by default. NEVER replace or delete a source unless the user explicitly authorizes replacement.
Runtime contract
- MUST require Node.js 18.17 or newer and
npmonPATH. - MUST treat the directory containing this file as
SKILL_ROOT. - MUST run
<SKILL_ROOT>/scripts/main.mjs; NEVER recreate the compression logic in an ad hoc command. - MUST allow the script to install the pinned Sharp runtime into the user's cache on first use. Installation diagnostics go to stderr; JSON results remain on stdout.
- MUST accept only static
.png,.jpg,.jpeg, and.webpinputs. NEVER download remote URLs or convert unsupported formats on the user's behalf.
Workflow
CREATE A TODO LIST FOR THE TASKS BELOW, then execute the steps in order.
-
Resolve exactly one local input path. If the request has no path, has multiple ambiguous paths, points to a URL, or requests an unsupported format or editing operation, stop and request a supported local file or directory.
-
Choose CLI options from the user's request:
- Default to WebP at quality 80 and keep the source.
- Use
--format pngfor PNG output and do not pass--quality; PNG output is lossless. - Add
--recursiveonly when the user explicitly asks to include subdirectories. - Add
--replaceonly when the user explicitly authorizes replacing the source files. - Use
--outputonly for one file, never for a directory, and never together with--replace.
-
Run the CLI with an absolute input path and
--json:node "<SKILL_ROOT>/scripts/main.mjs" "/absolute/input" --format webp --quality 80 --json -
Inspect the exit status and JSON. If the exit status is nonzero or
failuresis non-empty, report both successful and failed files and do not claim complete success. -
Verify every reported output path exists. For cross-format
--replace, also verify that the original path no longer exists. If either verification fails, report the missing or unexpected path and stop with failure. Otherwise report the absolute output paths, before/after byte counts, andsavedPercent, then end.
What ships with it
8 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.
- 11d ago First seen · 108 lines · 107 tokens per session scan A fd06ae6d5b31
compress-image is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,249 once invoked, about $0.0005 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
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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.