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 agentmods add skills/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-code-reviewnpx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-code-reviewgit clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-ToolkitWhat 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 | $0.00076 | $0.01089 |
| Opus 5 | $0.00038 | $0.00544 |
| Sonnet 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 2d 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
2 near-identical copies found in the catalogue:
- cloudbase-code-review — 100% identical, 0 lines differ
- cloudbase-code-review — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 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 the grader does.
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
11 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.
- 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.
- 2d ago First seen · 102 lines · 76 tokens per session scan A 4b45e2fe2a6b
cloudbase-code-review is a skill published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,087 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,089 once invoked, about $0.0004 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
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…