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 FlapPearLabs/zhihu-grabber-toolkit --skill zhihu-answer-grabbergit clone --depth 1 https://github.com/FlapPearLabs/zhihu-grabber-toolkitWrote 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/flappearlabs/zhihu-grabber-toolkit/zhihu-answer-grabber)<a href="https://agentmods.dev/skills/flappearlabs/zhihu-grabber-toolkit/zhihu-answer-grabber"><img src="https://agentmods.dev/badge/skills/flappearlabs/zhihu-grabber-toolkit/zhihu-answer-grabber/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/flappearlabs/zhihu-grabber-toolkit/zhihu-answer-grabber"><img src="https://agentmods.dev/badge/skills/flappearlabs/zhihu-grabber-toolkit/zhihu-answer-grabber.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 | $0.00105 | $0.03115 |
| Opus 5.5 | $0.00042 | $0.01246 |
| Sonnet 5.5 | $0.00021 | $0.00623 |
| Haiku 4.5 | $0.00011 | $0.00312 |
Grade A, and why
zhihu-answer-grabber 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 1mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
51 files 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.
- agents/openai.yaml 1.5 KB
- LICENSE 34 KB
- package-lock.json 3.2 KB
- package.json 642 B
- references/handoff-schema.md 3.7 KB
- references/security.md 3.6 KB
- references/usage.md 8.2 KB
- references/verification.md 4.7 KB
- scripts/browser-smoke-core.mjs 8.9 KB runs code
- scripts/browser-smoke.mjs 14 KB runs code
- scripts/make-handoff.mjs 3.4 KB runs code
- scripts/preflight.mjs 7.0 KB runs code
- scripts/verify-output.mjs 894 B runs code
- scripts/zhigrab.mjs 1.4 KB runs code
- src/asset-extractor.js 17 KB runs code
- src/cli.js 21 KB runs code
- src/config.js 4.5 KB runs code
- src/grabber.js 23 KB runs code
- src/http.js 9.1 KB runs code
- src/machine-paths.js 2.5 KB runs code
- src/markdown-security.js 20 KB runs code
- src/official.js 2.3 KB runs code
- src/render.js 5.2 KB runs code
- src/rich-renderer.js 20 KB runs code
- src/search-answer-count.js 3.1 KB runs code
- src/signer.js 6.1 KB runs code
- src/verifier.js 9.4 KB runs code
- test/asset-extractor.test.js 26 KB runs code
- test/b1-cross-volume.test.js 11 KB runs code
- test/batch-stability.test.js 11 KB runs code
- test/browser-smoke.test.js 13 KB runs code
- test/cli-entrypoint.test.js 4.2 KB runs code
- test/cli-json.test.js 27 KB runs code
- test/comments.test.js 22 KB runs code
- test/config.test.js 4.6 KB runs code
- test/count-mismatch-diagnostic.test.js 12 KB runs code
- test/grabber.test.js 10 KB runs code
- test/http.test.js 4.2 KB runs code
- test/make-handoff.test.js 3.7 KB runs code
- test/markdown-security.test.js 19 KB runs code
- test/preflight.test.js 7.8 KB runs code
- test/question-metadata.test.js 37 KB runs code
- test/render.test.js 2.5 KB runs code
- test/rich-renderer.test.js 35 KB runs code
- test/search-answer-count-cli.test.js 10 KB runs code
- test/search-answer-count.test.js 9.4 KB runs code
- test/signer.test.js 1.0 KB runs code
- test/skill-behavior.test.js 11 KB runs code
- test/v1-compat.test.js 6.5 KB runs code
- test/verifier-fence.test.js 3.3 KB runs code
- test/verify-output.test.js 9.3 KB runs code
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.
- 1mo ago First seen · 204 lines · 105 tokens per session scan A 4349954c0ac1
zhihu-answer-grabber is a skill published in the GitHub repository FlapPearLabs/zhihu-grabber-toolkit (6 stars, last pushed 9d ago), licensed AGPL-3.0. It adds 105 tokens to every session and 3,115 once invoked, about $0.0004 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.
Other skills, from other repositories
gem-pw
Browser-automated Gemini Gem CLI (CDP-first) — chat, CRUD, image gen, deep research, --collab surgical-diff review. No API key.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
browser
Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA…
agent-browser
Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.