Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/FlanChanXwO/pixiv-clinpx agentmods add skills/flanchanxwo/pixiv-cli/pixiv-cli-nativeWrote 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/flanchanxwo/pixiv-cli/pixiv-cli-native)<a href="https://agentmods.dev/skills/flanchanxwo/pixiv-cli/pixiv-cli-native"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-native/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/flanchanxwo/pixiv-cli/pixiv-cli-native"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-native.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 | $0.00064 | $0.00770 |
| Opus 5.5 | $0.00026 | $0.00308 |
| Sonnet 5.5 | $0.00013 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
pixiv-cli-native 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 22d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain pixiv-cli Native Code
Read AGENTS.md, the affected FFI/encoder owner, and the Rust/staticlib sections of docs/en/maintainers/development.md. Use ci/platforms.json for target/compiler/toolchain metadata; do not maintain a second platform list in a new helper or skill.
Change safely
- Identify whether the change affects Rust source, the C ABI, cgo selection, vendoring, staticlib provenance, or release linking. Record the affected behavior and evidence required before altering binary inputs.
- Use the repository's Red/Green workflow for behavior changes. Keep unsafe FFI ownership, allocation/free pairing, panic containment, cancellation, and error translation explicit. Avoid
unwrap/expecton fallible external input or crossing the FFI boundary with unwinding. - Work in
internal/media/ugoira/rustfor Cargo commands so its.cargo/config.tomlsource replacement applies. Use locked/offline dependency resolution. Never hand-edit vendored crates or hide a network fallback; approved dependency changes must regenerate the complete closure and license evidence. - Preserve the single encoder/FFI seam. A slow normal encode is not a timeout failure. Keep decoder-derived resource constraints and explicit errors; do not add another encoder or ffmpeg runtime fallback.
Verify the touched boundary
From the crate directory, run the appropriate focused test, then:
cargo fmt --check
cargo test --locked --offline
cargo clippy --locked --offline --all-targets -- -D warnings
From the repository root, relevant checks include:
go test ./internal/media/ugoira/staticlib -run '^TestCommittedManifestWhenPresent$' -count=1
go test ./internal/media/ugoira/... -count=1
go run ./scripts/cmd/licensebundle --check
sh scripts/test-build-staticlibs.sh
sh scripts/test-build-platform.sh
sh scripts/test-rust-vendor.sh
These commands can compile native code and consume significant resources; confirm the required existing toolchains and scope first. Report missing targets, compilers, or components instead of installing or pretending to validate them.
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.
- 22d ago First seen · 49 lines · 64 tokens per session scan A 7a49b676a78f
pixiv-cli-native is a skill published in the GitHub repository FlanChanXwO/pixiv-cli (134 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 770 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
rust-check
Run cargo check on the current Rust project to find compile errors.
go-rust-reverse
Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
printing-press
Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…
zapier-sdk
Zapier SDK for TypeScript. Programmatic access to 9,000+ apps on a user's behalf via Zapier's OAuth and audit layer. Use when writing code that needs to run actions in third-party apps (send an email, upsert a CRM record, look up a spreadsheet row, post to a chat) without managing per-app OAuth or vendor SDKs.…
scaffold-project
Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…