CloudBase AI Toolkit is an integration layer that lets AI coding tools use Tencent CloudBase as an application backend, including databases, authentication, functions, storage, and deployments. Developers use it to have coding agents build and operate CloudBase-backed applications through skills, plugins, commands, and chat-accessible tools. The catalogue entries are the toolkit’s own skills, agents, hooks, plugins, rules, instructions, and MCP tools.
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 TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-code-reviewgit clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-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/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-code-review)<a href="https://agentmods.dev/skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-code-review"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-code-review/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/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-code-review"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-code-review.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 | $0.00076 | $0.01092 |
| Opus 5.5 | $0.00030 | $0.00437 |
| Sonnet 5.5 | $0.00015 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
cloudbase-code-review 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 3d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- cloudbase-code-review — 100% identical, 0 lines differ
- cloudbase-code-review — 98% identical, 5 lines differ
- cloudbase-code-review — 91% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sibling skills (local only)
Sibling CloudBase skills ship beside this skill. Use local relative paths such as ../auth-tool-cloudbase/SKILL.md.
If a referenced sibling skill file is missing from this environment, ask the user to install the full CloudBase plugin (or the missing skill). Do not HTTP-fetch remote skill or protocol markdown into the agent context.
CloudBase Code Review
One-liner: After implementing CloudBase features, call this skill to catch common mistakes before users do.
When to use
Call this skill after completing a CloudBase implementation task, before declaring done:
- You implemented auth (login / register / route guard)
- You created database tables or wrote CRUD (NoSQL / PostgreSQL / MySQL)
- You set up CloudBase Storage (file upload, hosting)
- You configured security rules or RLS policies
- You wrote MCP-dependent code
- You wrote Cloud Function or CloudRun HTTP handlers (check for credential / header echo leaks)
How it works
The skill runs in two layers:
| Layer | Method | Speed | What it catches |
|---|---|---|---|
| Lint (optional) | No executable script is shipped. If the user approves running lint, review the code block in references/lint-rules/README.md, copy it to a temporary local cloudbase-lint.mjs, then run node cloudbase-lint.mjs --project-dir <path> |
Seconds | Deterministic regex checks — wrong API calls, missing configs, pattern mismatches |
| LLM review | Read each rule's "LLM 检查" section, inspect code semantically | Variable | Semantic issues — route guard logic, RLS completeness, architecture-level problems |
Rule index
See references/RULES_INDEX.md for the full matrix (module × frontend type → applicable rules).
Rule boundary
Do not promote a single failed run or case-specific workaround into a hard rule. A rule should be backed by stable SDK/API documentation, repeated failures, or deterministic runtime behavior. Case-specific observations belong in attribution reports; only broadly applicable constraints should enter RULES_INDEX.md or the optional lint checklist.
What ships with it
12 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.
- LICENSE.md 1.0 KB
- references/lint-rules/README.md 17 KB
- references/RULES_INDEX.md 13 KB
- references/rules/cross-cutting/AUTH001.md 2.4 KB
- references/rules/cross-cutting/SEC001.md 2.3 KB
- references/rules/cross-cutting/SKILL001.md 1.5 KB
- references/rules/postgresql/PG-CR001.md 2.7 KB
- references/rules/postgresql/PG-CR002.md 2.8 KB
- references/rules/postgresql/PG-CR003.md 1.9 KB
- references/rules/postgresql/PG-CR004.md 2.9 KB
- references/rules/postgresql/PG-CR005.md 2.3 KB
- references/rules/storage/STORAGE001.md 1.9 KB
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.
- 3d ago Changed bd1064366236
- 7d ago Changed · +1 lines cd3199f8af19
- 16d ago Changed 17af49f1a4e7
- 25d ago Changed eb521fe815b3
- 26d ago Changed b45a4a0a2eca
- 1mo ago Changed 00d052f91381
- 1mo ago Changed dfd5867f6d73
- 1mo ago Changed 1c3637b22867
- 1mo ago Changed e5465b21fe50
- 1mo ago First seen · 102 lines · 76 tokens per session scan A cbf21bd7be39
cloudbase-code-review is a skill published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,138 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,092 once invoked, about $0.0003 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
frontend-reviewer
Review frontend code, UI changes, generated implementations, and pull requests with severity-based findings and checklist-driven analysis. Use when auditing React/TypeScript/CSS code, validating AI-generated frontend output, performing acceptance review before merge, or checking whether a frontend change is safe to…
Baseline Security Checks
Check common security risks in application code (SQLi, XSS, secrets, open redirect).
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…