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 FlanChanXwO/pixiv-cli --skill pixiv-cli-developgit clone --depth 1 https://github.com/FlanChanXwO/pixiv-cliWrote 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-develop)<a href="https://agentmods.dev/skills/flanchanxwo/pixiv-cli/pixiv-cli-develop"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-develop/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-develop"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-develop.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 | $0.00062 | $0.01319 |
| Opus 5.5 | $0.00025 | $0.00528 |
| Sonnet 5.5 | $0.00012 | $0.00264 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
pixiv-cli-develop 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop pixiv-cli
Establish the change
Read root AGENTS.md, the relevant architecture section, the exact owner code, and its tests. State the observable result and what is outside scope. For a bug, reproduce it and trace input through the owner before proposing a fix. For ambiguous or cross-boundary work, settle compatibility, data ownership, and acceptance criteria first; a small explicit fix needs no design ceremony.
Inspect git status --short, branch, and base SHA. Reuse a suitable isolated worktree or create one at an unused agreed location with git worktree add -b BRANCH PATH BASE; substitute verified values, preserve other worktrees, and never reset someone else's changes. Set the working directory on every tool invocation.
Use available LSP definitions, references, callers, and impact analysis before changing symbols. If unavailable, report it, inspect imports/callers with targeted rg, and verify the affected packages with the compiler/tests. Read foundational documents and exact edited code yourself; delegated summaries are evidence, not design authority.
Go design and language rules
- Use the
go.modtoolchain andgofmt. Preserve Go initialisms, descriptive package names, and consistent receiver names. Document affected exported contracts, including cancellation, ownership, optional values, and side effects. Apply pixiv-cli-code-commenting to comments and numbered stages; English and Chinese prose are both acceptable, with valid Go doc syntax. - Prefer concrete types and existing owners. Define small interfaces at a real consumer seam, not one interface per implementation; avoid public abstractions introduced only for tests. Keep constructors explicit and side-effect boundaries visible.
- Keep Cobra, terminal input, JSON presentation, and exit handling in CLI owners. Keep MCP schema/presentation in its tool owner. Reuse shared records and traversal rather than copying pagination, filtering, or output rules into each adapter.
- Pass
context.Contextas the first parameter where cancellation applies and propagate it through requests and loops. The caller owns cancellation policy. Keep goroutine lifetime and resource closure explicit; avoid detached workers, shared mutable globals, and unbounded background activity. - Return contextual errors while preserving
errors.Is/errors.Asclassification. Do not log and return the same failure at every layer. Keep the SDK silent by default and redact at trust boundaries; never wrap a secret-bearing upstream response wholesale. - Distinguish absent, zero, empty, and invalid values when the wire contract does. Preserve unknown SDK fields where the record contract requires them. Do not fill unavailable upstream fields with invented defaults or advertise schema-only capabilities.
- Preserve atomic persistence and observable committed/unknown outcomes. Test credential revision races, cleanup, cancellation, and file permissions when those mechanisms change; do not claim rollback after a committed replacement.
- Optimize only against an observed cost or requested requirement. Prefer removal/reuse, standard-library or native features, existing dependencies, then a direct local implementation. Add a shared abstraction only when stable current uses make it simpler.
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 · 50 lines · 62 tokens per session scan A b92545e85f1a
pixiv-cli-develop is a skill published in the GitHub repository FlanChanXwO/pixiv-cli (134 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,319 once invoked, about $0.0002 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
commit-msg
You receive a git diff of staged changes via stdin. Generate a commit message.
check-linters-before-commit
Before any commit, run linters, vet, tests, and build verification; do not commit until checks pass.
pyo3-bindings
PyO3 conventions for exposing a Rust core to Python: pyclass/pymethods, PyErr/PyResult error mapping, GIL release, properties, maturin builds, and pytest. Load when generating or reviewing PyO3 Python bindings for a Rust library.
pr-writer
Writes a pull-request description from the actual diff.
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.
csv
CSV data processing — view, filter, convert, merge tabular data. Zero barrier — use with x-cmd, Python, or awk. Use for "csv", "data", "table", "spreadsheet", "conversion".