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 agentmods add skills/imgproxy/imgproxy-js-core/imgproxy-docs-syncnpx skills add imgproxy/imgproxy-js-core --skill imgproxy-docs-syncgit clone --depth 1 https://github.com/imgproxy/imgproxy-js-coreWhat 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 | $0.00090 | $0.02585 |
| Opus 5 | $0.00045 | $0.01293 |
| Sonnet 5 | $0.00018 | $0.00517 |
| Haiku 4.5 | $0.00009 | $0.00259 |
Grade A, and why
imgproxy-docs-sync 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 2d 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 -sL https://github.com/imgproxy/imgproxy-docs/compare/<base>...<head>.diff` How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imgproxy docs sync
Turn an upstream docs-update issue into a reviewed code change and a PR.
The imgproxy-docs repo fires a repository_dispatch at this repo whenever the Usage
section of the docs changes. .github/workflows/imgproxy-usage-updated.yml opens an issue
from .github/templates/ISSUE.md, always titled "Usage docs of imgproxy have been updated"
and always shaped like this:
@DarthSim has just updated the [Usage](https://docs.imgproxy.net/category/usage) part of the documentation.
Please, check [the difference](https://github.com/imgproxy/imgproxy-docs/compare/451581c87fd8...6c7c0312f7f0) and make the necessary changes.
The whole job is: read that diff, decide what it means for this package, get sign-off, ship it.
Input
The skill argument is an issue number (83), an issue URL, or nothing.
- Nothing given — list the candidates and ask which one:
gh issue list --state open --search "Usage docs of imgproxy have been updated" --json number,title,createdAtIf several are open, note that they are sequential: issue N'sbasesha is usually issue N-1'sheadsha. Offer to process the oldest first, or to collapse the whole run into one range (oldestbase… newesthead) and one PR. Don't decide this silently — ask. - Issue given — go straight to step 1.
Step 1 — Read the issue and extract the compare range
gh issue view <N> --json number,title,body,state,url
Pull the two shas out of the the difference link:
https://github.com/imgproxy/imgproxy-docs/compare/<base>...<head>.
Bail out early and tell the user if: the issue is already closed, its body has no compare link
(a hand-written issue — this skill doesn't apply, handle it normally), or a PR already references
it (gh pr list --state all --search "<N>").
Step 2 — Get the upstream diff
gh api repos/imgproxy/imgproxy-docs/compare/<base>...<head> \
--jq '.files[] | {filename, status, additions, deletions}'
Then read the patches for **docs/usage/** only**:
What ships with it
1 file 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.
- 2d ago First seen · 225 lines · 90 tokens per session scan A 12336f852299
imgproxy-docs-sync is a skill published in the GitHub repository imgproxy/imgproxy-js-core (11 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 2,585 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…