seekdb is a MySQL-compatible database for AI agents that stores vector, text, structured, and semi-structured data in one engine, with embedded and server modes. Agents and their developers use it for state storage and hybrid search. The catalogue entries provide instructions and skills for working with seekdb.
Borrowing it
Nothing to install: this file belongs to oceanbase/seekdb. 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/oceanbase/seekdb/master/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/oceanbase/seekdbWrote 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/oceanbase/seekdb/code-review)<a href="https://agentmods.dev/skills/oceanbase/seekdb/code-review"><img src="https://agentmods.dev/badge/skills/oceanbase/seekdb/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/oceanbase/seekdb/code-review"><img src="https://agentmods.dev/badge/skills/oceanbase/seekdb/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 73 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- low Privilege Escalation · line 88 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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 | $0.00082 | $0.01689 |
| Opus 5.5 | $0.00033 | $0.00676 |
| Sonnet 5.5 | $0.00016 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
code-review scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
caches, `curl` or `wget`, or third-party steps can disclose or transmit them. How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SeekDB Code Review
Review Goal
Act as a senior seekdb maintainer. Find concrete defects that can affect users, operators, data correctness, availability, security, or material performance. Prefer no comment over an uncertain style preference or speculative cleanup.
Write review comments in English.
Establish the Contract
- Read the pull request title, description, linked issue, changed tests, and available CI results.
- State the behavior the change promises before judging its implementation.
- Inspect enough surrounding code to understand the existing invariant. Do not review the diff in isolation.
- Trace the changed invariant through relevant callers, callees, sibling implementations, and unchanged paths. Follow all representations of the affected value, state, or operation across component boundaries.
- When behavior is unclear, use a concrete input, state, and execution sequence to prove the defect. If proof is incomplete but the potential impact is serious, state exactly what evidence or focused test is missing.
Required Checks
- Error propagation: Check
ret,OB_FAIL, andOB_SUCCflows for lost or overwritten errors, work continuing after failure, incorrect success returns, partial side effects, and missing cleanup. Recognize established seekdb error-handling idioms and flag only behavior-changing mistakes. - Memory and resources: Verify allocator ownership and lifetime, arena-backed pointer escape, object destruction, and release of memory, file descriptors, sockets, threads, futures, tasks, and timers on success and failure paths.
- Concurrency and lifecycle: Check synchronization, lock ordering, atomic state, task cancellation, retries, startup, shutdown, and callbacks or work that can continue after ownership or state changes.
- Current-version state consistency: Follow tablet/LS state, log replay, transaction state, schema state, and cache state through normal and partial failure paths. Verify related in-memory representations cannot diverge.
- SQL semantics: When parser, resolver, rewrite, optimizer, or executor code changes, check equivalent syntax and expression forms, aliases, NULL and boundary behavior, and every relevant stage that carries the same semantic.
- Rust and networking: Check transport errors, protocol handling, resource cleanup, and platform-specific behavior for supported Linux and Windows paths. Require focused Rust tests for changed behavior when practical.
- Security: Apply the dedicated security review below to product code, workflows, build scripts, tests, documentation, and repository instructions.
- Performance: Report material regressions in hot paths, such as repeated allocation, avoidable copying, quadratic work, excessive locking, blocking I/O, or expensive work added to high-frequency operations. Do not report unmeasured micro-optimizations.
- Tests and evidence: Require the smallest focused unit test, mysqltest, Rust test, benchmark, or measurement that would fail if the changed invariant were broken. Do not demand broad tests that cannot prove the behavior.
- Build and CI: Review build or workflow changes only for correctness, security, portability, or reliability problems, not stylistic preferences.
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 · 147 lines · 82 tokens per session scan A 49bb0bcd7992
code-review is a skill published in the GitHub repository oceanbase/seekdb (3,201 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,689 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.
Other skills, from other repositories
sqlike
Check SQL with sqlike — deterministic static analysis (validity, anti-patterns, rewrites, index advice) and query-equivalence verification. Use whenever you write, edit, review, or rewrite a SQL query, or need to prove two queries return the same results. Requires the sqlike MCP server (@sqlike/mcp) or the sqlike CLI…
prisma-docs
Prisma ORM 7.x — schema, Prisma Client CRUD, migrations, introspection, relations, transactions, TypeScript.
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
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…