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 MirandaKim1434/spider-data --skill skillgit clone --depth 1 https://github.com/MirandaKim1434/spider-dataWrote 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/mirandakim1434/spider-data/skill)<a href="https://agentmods.dev/skills/mirandakim1434/spider-data/skill"><img src="https://agentmods.dev/badge/skills/mirandakim1434/spider-data/skill/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/mirandakim1434/spider-data/skill"><img src="https://agentmods.dev/badge/skills/mirandakim1434/spider-data/skill.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 | $0.00119 | $0.01101 |
| Opus 5.5 | $0.00048 | $0.00440 |
| Sonnet 5.5 | $0.00024 | $0.00220 |
| Haiku 4.5 | $0.00012 | $0.00110 |
Grade A, and why
spider-data 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 2mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spider-data
All web access goes through one CLI. WebSearch and WebFetch are denied by
policy and will not run.
spider-data search "<query>" [--num 8] [--json]
spider-data fetch "<url>" [--format md|html|text] [--json]
spider-data crawl "<url>" [--limit 20]
Add --json when you want to branch on the result programmatically. Without it
you get readable text.
Branch on the exit code, never on the wording
Every failure has a stable code. Read it and act; do not re-read the prose and guess.
| Exit | Meaning | What to do |
|---|---|---|
| 0 | Success — including a search that matched nothing | Use the result |
| 3 | Cross-site redirect, not followed | Re-run fetch on the redirect_to value if you still want it |
| 4 | The target refuses anonymous access (bot wall, login wall, paywall) | The ladder already tried. Find another source |
| 5 | The page does not exist | Do not retry. Fix the URL or search for the real one |
| 6 | Transient | Retry once, later. If it repeats, move on |
| 7 | The API key is wrong or missing | Stop and tell the user to run spider-data auth login |
| 8 | No spider.cloud credit left | Stop and tell the user. Do not keep trying |
| 9 | Rate limited | Wait, then retry once |
| 10 | Refused locally (SSRF guard, robots.txt, bad scheme) | Do not work around it. This is a deliberate boundary |
Exits 5, 7, 8 and 10 are terminal. Retrying them wastes time or money and changes nothing.
Zero results is an answer
spider-data search exiting 0 with an empty list means the query genuinely
matched nothing. It does not mean the tool failed.
Reword and re-run at most once. Each search is a paid call, and a query with no answer still has no answer the fifth time. Say the search found nothing and move on to a different approach.
Long pages: read the outline, then drill in for free
A long page comes back as a section outline plus as much text as fits. The full text is already cached, so these follow-ups cost nothing and make no API call:
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.
- 2mo ago First seen · 105 lines · 119 tokens per session scan A cc285fd0e2ac
spider-data is a skill published in the GitHub repository MirandaKim1434/spider-data (0 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 1,101 once invoked, about $0.0005 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 2026-08-31.
spider-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spider-dataMirandaKim1434/spider-data | Skill | 0 | 2mo ago | MIT | A | 119 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | 2d ago | Apache-2.0 | A | 48 | Claude Code, Codex |
| review-implement-phaseprisma/orm | Skill | 48k | 2d ago | Apache-2.0 | A | 38 | Claude Code |
| no-bare-castsprisma/orm | Skill | 48k | 2d ago | Apache-2.0 | A | 52 | Claude Code, Codex |
| write-architecture-docsprisma/orm | Skill | 48k | 2d ago | Apache-2.0 | A | 55 | Claude Code, Codex |
| Workspace Data AnalystVoltAgent/voltagent | Skill | 11k | 2d ago | MIT | A | 14 | Claude Code, Codex |
| featurevisorfeaturevisor/featurevisor | Skill | 814 | 4d ago | MIT | A | 131 | Claude Code, Codex |