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-cigit 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-ci)<a href="https://agentmods.dev/skills/flanchanxwo/pixiv-cli/pixiv-cli-ci"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-ci/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-ci"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-ci.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 | $0.00061 | $0.01043 |
| Opus 5.5 | $0.00024 | $0.00417 |
| Sonnet 5.5 | $0.00012 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
pixiv-cli-ci 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose pixiv-cli CI
Read AGENTS.md, the exact changed workflow, and its invoked script/tool. Workflow YAML owns ordering, inputs, permissions, and conditions; ci/platforms.json plus tools/platformmatrix own platform selection. Do not infer executable policy from a historical plan or a skill's old command example.
Identify the failure
Use the connected GitHub tools or an already available authenticated gh. Establish repository, PR/head SHA, workflow, run ID, attempt, event, job, and failing step. Read the first causal error and relevant surrounding log, not just the final failure line. Never display tokens, account stores, signed URLs, or raw secret-bearing responses.
Useful read-only commands, with verified placeholders, are:
gh pr checks PR_NUMBER
gh run view RUN_ID --json name,event,headBranch,headSha,status,conclusion,jobs,url
gh run view RUN_ID --log-failed
gh run view --job JOB_ID --log
Classify deterministic code/contract failure, missing environment, upstream/network failure, cancellation, or genuine infrastructure flakiness. A long-running job is not automatically hung. Gather bounded relevant output, but preserve complete logs where needed instead of truncating source evidence.
Select the owning checks
Use pixiv-cli-test for local reproduction. ci.yml owns the read-only, untrusted Quality gate. Trusted pr-metadata.yml checks out current base-branch policy, validates template/command declarations, classifies the PR, dispatches base-ref Platform/Container workers, and owns the real job-level Platform smoke / Container smoke required checks. Its distinct * smoke worker Check Runs are only the trusted result bridge consumed by those gate jobs. Only worker matrix jobs execute the exact PR head with read-only permissions. Preserve the fork-safe boundary and classifier. Run relevant safely independent downstream phases if fail-fast hid their results.
Inspect the exact PR SHA: Quality gate, Platform smoke, and Container smoke are GitHub Actions jobs; PR template gate / PR commands gate are commit statuses. Unneeded Quality or smoke jobs must display Skipped, not synthetic success. Required smoke jobs wait for the distinct trusted Platform smoke worker / Container smoke worker Check Runs that are completed by the base-ref worker workflows. Body-only PR edits reclassify the unchanged head and mirror its existing worker result rather than creating a bypassing skip. Filtering workflow runs only by PR head can miss the worker runs themselves. Ordinary branch/main pushes do not run CI; matching tag pushes use Quality and Release rather than duplicate PR smoke matrices.
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.
- 4d ago Changed 891d7912abc4
- 29d ago Changed · -93 lines · -21 tokens per session 5bae44eb8a2f
- 1mo ago Changed · +3 lines 7c9b856ce2df
- 1mo ago Changed · -1 lines 01c867ca24b9
- 1mo ago First seen · 137 lines · 82 tokens per session scan A 1ffbc2a4bae1
pixiv-cli-ci is a skill published in the GitHub repository FlanChanXwO/pixiv-cli (133 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,043 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
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.
gh
Patterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
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…
release
Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.
commit-msg
You receive a git diff of staged changes via stdin. Generate a commit message.