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 instructions/flanchanxwo/pixiv-cli/agents-mdgit 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/instructions/flanchanxwo/pixiv-cli/agents-md)<a href="https://agentmods.dev/instructions/flanchanxwo/pixiv-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/flanchanxwo/pixiv-cli/agents-md.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 | $0.01666 | $0.01666 |
| Opus 5 | $0.00833 | $0.00833 |
| Sonnet 5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
pixiv-cli AGENTS.md 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 4d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
这是一个 Go 版 Pixiv CLI 与 MCP stdio server。它通过 pixiv CLI 和 pixiv mcp 暴露 Pixiv 搜索、详情、排行、推荐、用户、收藏、下载、token refresh 和缩略图能力，通过 pixiv fanbox CLI 与 pixiv fanbox mcp 暴露 FANBOX 能力。公开能力只来自 sdk、sdk/pixiv、sdk/fanbox。
核心命令
go test ./...
sh scripts/build.sh
真实 SDK e2e 默认跳过；需要本机凭据时显式运行（Pixiv 读本地 pixiv-cli.db 选中账号，FANBOX 读 macOS Keychain 授权 session）：
PIXIV_SDK_E2E=1 go test ./e2e -run TestRealPixivSDKRead -count=1 -v
FANBOX_E2E_CREATOR_ID=<non-secret-creator-id> FANBOX_E2E_TAG=<non-secret-tag> \
FANBOX_E2E_POST_ID=<non-secret-post-id> FANBOX_E2E_POST_URL=<non-secret-post-url> \
FANBOX_SDK_E2E=1 go test ./e2e -run TestRealFanboxSDKRead -count=1 -v
FANBOX E2E target variables are explicit non-secret test targets; the session remains in the macOS Keychain.
TestRealFanboxSDKRead 是唯一可以记为「完整 FANBOX read」的测试，它强制要求 post 目标带 first-party file attachment。TestRealFanboxSDKPostInfo（额外需要 FANBOX_E2E_POST_ONLY=1）只覆盖 Post/body/ResolveURL，通过时记为 partial-pass，不得替代完整 read 的状态。
边界规则
各包职责描述见 docs/zh-CN/maintainers/architecture.md；以下是不可违反的规则：
cmd/pixiv只委托internal/cli；internal/cli/root.go负责命令树、全局生命周期与生产组装，具体命令位于internal/cli/commands及其 Pixiv/FANBOX owner 子目录，不恢复旧 resource graph/requirements 层。- CLI/MCP 的 Pixiv/FANBOX 能力只经公开
sdk/pixiv、sdk/fanbox及 owner-local 窄端口调用；不得直连internal/services/{pixiv,fanbox}协议适配包。 - reverse-search is the only cross-boundary exception：生产组装仅允许
internal/cli/root.go依赖internal/services/reversesearch/assembly；internal/cli/commands与internal/mcpserver只能依赖internal/services/reversesearch顶层契约，不得导入internal/services/reversesearch/saucenao、internal/services/reversesearch/ascii2d或其他其子包。provider 协议构造、HTTP client、凭据与代理只由 composition root/assembly 持有。 - MCP 聚合与输入/输出适配在
internal/mcpserver/{pixiv,fanbox}，具体 tool 位于各自tools/<tool>；stdio runtime 由 CLI MCP 命令启动。 internal/shared/*承载跨命令共享机制，internal/utils/{parse,text,uri}保持协议无关；配置 schema/snapshot 在internal/config/settings，本地路径和权限在internal/config/paths，文件机制在internal/storage/file/*。- 测试文件遵循
docs/zh-CN/maintainers/development.md测试文件布局的 same-stem、平台后缀和 same-package 例外规则；该节是唯一 canonical test-layout 规则。
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.
- 4d ago First seen · 57 lines · 1,666 tokens per session scan A 5532cb64fb55
pixiv-cli AGENTS.md is an instructions file published in the GitHub repository FlanChanXwO/pixiv-cli (130 stars, last pushed yesterday), licensed MIT. It adds 1,666 tokens to every session, about $0.0083 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 2026-08-30.
Other instructions, from other repositories
sdk AGENTS.md
Instructions for zapier/sdk, covering agents.md, what this repo is, files to read before you start, when to use this sdk vs. alternatives and setup.
sdk CLAUDE.md
Instructions for zapier/sdk, a project described as: Agent-readable docs, verified examples, and skill manifest for @zapier/zapier-sdk.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.