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.
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.
curl -O https://raw.githubusercontent.com/whiteguo233/OpenBiliClaw/main/.claude/skills/add-platform-source/SKILL.mdgit clone --depth 1 https://github.com/whiteguo233/OpenBiliClawWrote 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/whiteguo233/openbiliclaw/add-platform-source)<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/add-platform-source"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/add-platform-source.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01478 |
| Opus 5 | $0.00027 | $0.00739 |
| Sonnet 5 | $0.00011 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
add-platform-source 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 today.
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.
Add Platform Source
Deliver the requested source capability through the actual product path. Use docs/platform-source-integration.md as the shared guide and docs/platform-source-history-lessons.md to find failure precedents. Paths below are relative to the repository root. Historical sessions and plans are evidence, not current instructions or proof that a missing capability is still missing.
Select the scope and reading
Declare full, discovery-only, capability-increment, or audit-only. Plain “add a source” means full; a repair stays within the affected capability. Research/audit does not authorize implementation. Updating this skill requires documentation and skill validation, not a new platform contract or live account E2E.
Read the guide's execution protocol and completion criteria, then select the relevant sections:
| Work | Guide sections and useful precedents |
|---|---|
| New source | §0 contract, §1 upstream spike, registration map; select the remaining sections by capability |
| Auth / identity / settings | §0.1–0.7, §4–5; Bangumi/GitHub optional credentials, V2EX/Linux.do/Weibo capability readiness |
| Browser tasks / account signals | §2–3, §5; staged completion, MV3 recovery, incremental opt-in and task isolation |
| API / Feed / discovery | §1, §6–6.5; GitHub pagination/cooldown, keyword dual-track, shared admission |
| Cards / native save | §7–9; DTO-to-renderer evidence, exact identity and persisted save confirmation |
| Validation / delivery | §8–11; scoped tests, installed artifact provenance, separate E2E chains and documentation |
For full integration, scan the whole guide's capability headings for omissions. For a narrow repair, expand to adjacent sections only when the diff crosses those boundaries; do not reopen unrelated platform implementations.
Execute with evidence
- Preserve existing changes and use the repository's worktree rule for implementation. Record the baseline. Before tests or E2E, prove Python imports, CLI, backend config/data roots and any installed extension resolve to the intended checkout; reload alone does not deploy a worktree build.
- Start with the relevant history-index rows, then inspect first integration and follow-up repairs in
git log --alland current tests. Read available project sessions/PRs only to fill a concrete evidence gap. Distinguish root user requests from delegated reviews, and merged fixes from in-flight branches. Never copy credentials, private account data, raw transcripts, or historical authorization into the task. - For a new source, copy the contract and acceptance templates. For an increment, reuse/update its contract and record the changed gates. Keep applicability (
requiredorN/A, with evidence) separate from execution (PASS,FAIL,NOT_RUN, orBLOCKED). Capability exclusions need executable proof where enforceable; out-of-scope mutations need scope evidence.deferredand missing E2E are neverN/A. - Probe the changed upstream path read-only before inventing fixtures. Preserve redacted success, pagination/termination and counterexamples. Anonymous success does not prove authenticated pagination, current-account ownership, private bootstrap, or the installed dispatcher. If one route is unavailable, record that boundary and continue independent work within the requested contract.
- Implement vertical slices: registry/contract → transport/normalization → event/bootstrap → formal discover/eval → config/status/init → surfaces. Reuse shared backend contracts and choose precedents per capability. Validate behavior at each affected boundary.
- For source wiring, run the audit with the repository Python 3.11+ interpreter:
PYTHONPATH="$PWD/src" "$SOURCE_SKILL_PYTHON" scripts/audit_platform_source.py --contract <contract> --check --json. Audit PASS proves registration evidence only. Review omissions against the raw contract, diff and artifacts; use an independent reviewer when requested or when the integration's risk warrants an authorized review, not as a mandatory extra process for every repair. - Record commands, exits and evidence levels in an acceptance copy. Only all-required
PASSearnscompletefor the declared scope. Reportincremental onlyfor usable work with missing required proof, orblockedfor work that cannot proceed. An audit/repair being complete does not certify the entire source. Report implemented, tested, merged, installed and released states separately.
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.
- today Changed · +12 lines · -20 tokens per session 8d3896035387
- 8d ago First seen · 34 lines · 74 tokens per session scan A 9f24997f07c9
add-platform-source is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,215 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,478 once invoked, about $0.0003 per session on Opus 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
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
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…
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
developing-genkit-tooling
Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency guidelines.