OpenBiliClaw: Skill for Claude Code

.claude/skills/verify/SKILL.md

verify is a skill for Claude Code from whiteguo233/OpenBiliClaw. It costs 20 tokens per session (599 once invoked), scanned C, original, MIT.

Instructions for verifying backend and web changes by running a real API server against an isolated temporary project. End-to-end verification checks that connected parts work together, rather than testing one function alone.

In plain words
What is it for?
Use it to start throwaway API instances, prepare test configuration and data, check behavior, and clean up after verification.
Why use it?
It avoids disturbing the production server and gives repeatable checks for different backend states.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is whiteguo233/OpenBiliClaw's own configuration. It tells Claude Code how to work on OpenBiliClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenBiliClaw configures →

About the project

OpenBiliClaw is a local, open-source AI agent that learns a person's interests and discovers content across multiple social platforms and the open web. It is for people who want personalized content recommendations with their usage data kept on their own machine.

whiteguo233/OpenBiliClaw · 3,215 stars · on GitHub · whiteguo233.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to whiteguo233/OpenBiliClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/whiteguo233/OpenBiliClaw/main/.claude/skills/verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/whiteguo233/OpenBiliClaw

Made for: Claude Code.

Wrote 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.

agentmods badge for verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/verify.svg)](https://agentmods.dev/skills/whiteguo233/openbiliclaw/verify)
Your own site
<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/verify"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 599 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 32
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Data Exfiltration · line 37
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00599
Opus 5 $0.00010 $0.00300
Sonnet 5 $0.00004 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 8d ago against content hash 218c67e06e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

verify scanned grade C with 2 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

(`lsof -nP -iTCP:846x -sTCP:LISTEN`), `rm -rf` the tmp roots. Zombie temp

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. **Probe with `curl --noproxy '*'`** — the local proxy/TUN hijacks loopback
.claude/skills/verify/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifying OpenBiliClaw backend changes end-to-end

Port 8420 is the user's production backend — never restart or reuse it. Spin up throwaway serve-api instances on spare ports (846x) against isolated project roots instead, and always kill them when done.

Recipe

  1. Isolated project root: mktemp -d /tmp/obc-verify.XXXXXX, put a minimal config.toml + empty data/ inside, point OPENBILICLAW_PROJECT_ROOT at it. data_dir = "data" resolves against that root.

  2. Craft the backend state you need via config/data, not mocks:

    • Configured but uninitialized: any provider section with a dummy api_key (registry build does not call the network at startup).
    • Degraded (llm_registry_unavailable): all provider keys empty and launch with env -u OPENAI_API_KEY -u ANTHROPIC_API_KEY -u GOOGLE_API_KEY -u GEMINI_API_KEY — ambient keys silently un-degrade it.
    • Initialized (profile ready): copy the real data/memory/soul.json into the tmp root's data/memory/ before launch. is_profile_ready() == "soul memory layer has data", loaded at startup (don't hot-drop the file into a running instance and expect it to flip).
  3. Launch (background, stdin must be closed or it hangs):

    OPENBILICLAW_PROJECT_ROOT=/tmp/obc-verify.XXX/a \
      nohup .venv/bin/openbiliclaw serve-api --host 127.0.0.1 --port 8461 \
      > /tmp/obc-verify.XXX/a/server.log 2>&1 < /dev/null &
    

    Ready in ~5-8s. Use the main repo's .venv/bin/openbiliclaw.

  4. Probe with curl --noproxy '*' — the local proxy/TUN hijacks loopback otherwise. curl -D - for redirect headers, /api/health to confirm the state you crafted (status, profile_ready), server.log for the "started in degraded mode" line.

  5. Clean up: kill the PIDs, confirm nothing listens on the ports (lsof -nP -iTCP:846x -sTCP:LISTEN), rm -rf the tmp roots. Zombie temp serve-api instances have corrupted real user data before — never skip this.

Read the full file on GitHub · 45 lines

Changes

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.

  1. 8d ago First seen · 45 lines · 20 tokens per session scan C 218c67e06e26

Subscribe to this mod's changes

verify is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,215 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 599 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

pw-api-pom

Maintain API services, API specs, shared fixtures, and auth/API session setup for the playwright-agentic-automation Playwright framework. Use when tasks touch api/services, api/specs, TestFixtures, auth token flows, role sessions, or route constants in the API automation layer.

Mallikarjun-Roddannavar/playwright-agentic-automation · 64 tokens

itemized-functions

Generate exhaustive integration functions with comprehensive test suites for all 3rd-party APIs and external services. Automatically creates function wrappers, individual test files, integrated test runners, and a detailed report of API behavior, response signatures, latency, and failure modes.

harshitsinghbhandari/domain-expansion · 53 tokens

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

ronmkr/PromptBook · 42 tokens

dogfood

Exploratory QA of web apps: find bugs, evidence, reports.

NousResearch/hermes-agent · 18 tokens

mem0-test-integration

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…

mem0ai/mem0 · 207 tokens

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

VoltAgent/voltagent · 52 tokens