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-reviewgit 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-review)<a href="https://agentmods.dev/skills/flanchanxwo/pixiv-cli/pixiv-cli-review"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-review/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-review"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00925 |
| Opus 5.5 | $0.00023 | $0.00370 |
| Sonnet 5.5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
pixiv-cli-review 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 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.
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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review pixiv-cli
Fix the review boundary
Inspect git status --short, git diff --stat, and the actual diff. For a PR/commit range, identify base and head SHAs and review that exact range; an empty working diff does not mean the PR has no changes. Read the originating requirement and relevant AGENTS.md routes. Do not guess the review range or treat another agent's summary as evidence.
Require each changed path to serve the requested result or an affected durable contract. Flag incidental planning notes, local evidence, temporary probes, and unrelated cleanup for removal from the PR; use PR scope checks.
Review the change, not an imagined framework
- Behavior: trace changed inputs to outputs and compare with acceptance criteria. Check CLI text/JSON/NDJSON, record identity, logical pagination, optional fields, typed errors, and command-specific defaults. Verify local search filters are not falsely passed upstream.
- Architecture/Go: apply the develop rules. Check real ownership, interface necessity, context/goroutine lifetime, error classification, and that public SDK changes are intentional and listed for the changelog. Prefer deleting speculative machinery; length alone is not a finding.
- Structure and naming: apply naming and placement. Flag vague names, dependency bags, forwarding function fields, test-only exported seams, retained internal compatibility paths, code placed where its container's name no longer describes it, and new files without a header comment.
- Security/state: check secret redaction, SQL/query boundaries, credential revision transactions, atomic writes and commit outcomes, permissions, URL/redirect policy, and trusted-local versus remote input assumptions. Preserve explicitly supported private resource routes rather than applying a blanket network ban.
- MCP: verify schema validation, SDK routing, separate Pixiv/FANBOX runtimes, protocol-clean stdio, authenticated HTTP, capability-specific registration and structured errors. Use the MCP workflow for changes at that boundary.
- Native/release: use native or CI only when touched. Review source/artifact identity, platform evidence, permissions, and immutable handoffs, not exact YAML formatting or arbitrary job counts.
- Tests/docs: apply the seven-contract checklist and caps. Require the owning checklist row and missing scenario before requesting permanent test code; use ignored probes for other investigations. Check CI-selected tests/support remain verbatim during rewrites, and apply the removal criteria. Preserve actual Red/Green and relevant regression evidence; live verification is manual and requires explicit authorization.
- Readability: apply the commenting rules. Check whether an extraction reduces total mental effort rather than just line count; reject noisy per-line comments, unsupported guarantees, and mandatory stage numbering. Either source-comment language is acceptable. Preserve machine-consumed directives and affected locale/product contracts.
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 Changed 6613e6dc42cf
- 5d ago Changed · +1 lines 84e54b996eb2
- 10d ago Changed · +2 lines 68006c863b1d
- 11d ago Changed 3372afe78719
- 1mo ago Changed · -65 lines · -5 tokens per session 06de88ed450b
- 1mo ago First seen · 94 lines · 63 tokens per session scan A 50d3feb15721
pixiv-cli-review is a skill published in the GitHub repository FlanChanXwO/pixiv-cli (133 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 925 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 2026-08-30.
Other skills, from other repositories
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
code-review-pi
Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.
go-conventions
Go code conventions covering Effective Go, error wrapping, golangci-lint, govulncheck, table-driven tests, interfaces, context usage, modules, and concurrency. Load when writing or reviewing Go code.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.