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 Cerdore/gdb-cli --skill database-core-debugginggit clone --depth 1 https://github.com/Cerdore/gdb-cliWrote 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/cerdore/gdb-cli/database-core-debugging)<a href="https://agentmods.dev/skills/cerdore/gdb-cli/database-core-debugging"><img src="https://agentmods.dev/badge/skills/cerdore/gdb-cli/database-core-debugging/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/cerdore/gdb-cli/database-core-debugging"><img src="https://agentmods.dev/badge/skills/cerdore/gdb-cli/database-core-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00064 | $0.01388 |
| Opus 5.5 | $0.00026 | $0.00555 |
| Sonnet 5.5 | $0.00013 | $0.00278 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
db-core-debugging 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 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.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DB Core Debugging Skill
自动化分析 Database core dump 文件的工作流程。
核心工作流
Step 0: 环境检查
gdb-cli env-check
- 若
gdb-cli命令不存在 → 安装：pip install git+http://gitlab.internal.example.com/tools/gdb_cli.git - 核对 GDB 版本：el7/el8 需要 9.0+，el9/Rocky 需要 15+
- 核对 GDB Python 支持：
gdb -batch -ex "python print('ok')"
Step 1: 加载 core dump（渐进式超时重试）
大型 DB binary（6.1G+）加载时间不可预测，采用渐进式超时：
第 1 次：gdb-cli load -b <binary> -c <core> --timeout 120 （2分钟）
若超时 → 第 2 次：gdb-cli load -b <binary> -c <core> --timeout 300 （5分钟）
若仍超时 → 第 3 次：gdb-cli load -b <binary> -c <core> --timeout 600 （10分钟）
仍失败 → 报错并提示可能原因
加载失败排查：
- 不要把 server.debug 当二进制用 → 正确用法：
gdb-cli load -b server -c core.xxx - debuginfo 缺失 → 把 server.debug 文件 copy 到 server 二进制同一目录下
- 二进制不匹配 → 确认 arm/x86 架构一致、版本完全匹配
- 跨机器动态库问题 → 使用
--sysroot或--solib-prefix参数 - GDB 版本问题 → 使用
--gdb-path指定正确版本 - core 文件不完整 → 检查磁盘空间，对比进程内存占用
Step 2: 状态概览
gdb-cli status -s <session_id>
确认：模式（core）、binary 路径、线程数、当前帧信息。
Step 3: 崩溃线程定位
gdb-cli threads -s <SID> --limit 50
找到信号线程（通常是 thread 1，收到 SIGSEGV/SIGABRT）。
Step 4: 堆栈分析
gdb-cli bt -s <SID> --thread <crash_thread> --limit 30
从崩溃帧（frame 0）向上遍历调用链，识别关键函数。
Step 4.5: 源码关联分析（可选）
如果 bt 输出包含源文件信息：
- 尝试在本地工作目录查找对应源码文件
- 使用 Read 工具读取崩溃位置前后 20 行代码
- 结合代码逻辑理解崩溃上下文
Step 5: 变量与上下文检查
# 崩溃帧的函数参数
gdb-cli args -s <SID> --thread <crash_thread> --frame 0
# 崩溃帧的局部变量
gdb-cli locals-cmd -s <SID> --thread <crash_thread> --frame 0
# 深入查看关键变量（需先切换上下文）
gdb-cli thread-switch -s <SID> <crash_thread>
gdb-cli frame -s <SID> 0
gdb-cli eval-cmd -s <SID> "this->member_name_"
gdb-cli eval-cmd -s <SID> "*ptr"
Step 6: 深入诊断
根据崩溃类型选择诊断手段：
| 崩溃类型 | 诊断命令 |
|---|---|
| 空指针解引用 | eval-cmd 检查指针值，ptype 查看类型 |
| 内存越界 | memory 检查周边内存，registers 查看地址寄存器 |
| 非法指令 | disasm 查看崩溃点汇编，registers 查看 rip |
| 栈溢出 | registers 查看 rsp，memory 检查栈边界 |
| 断言失败 | eval-cmd 查看断言条件中的变量值 |
Step 7: 根因推断 + 输出结论
What ships with it
1 file 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.
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 · 132 lines · 64 tokens per session scan A 6d0eddbb5985
db-core-debugging is a skill published in the GitHub repository Cerdore/gdb-cli (35 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,388 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
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
postgresql-indexing
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
axiom-audit-grdb-performance
Use when the user mentions GRDB performance review, slow GRDB queries, app-group database setup audit, a ValueObservation that stopped updating, or pre-release GRDB scan.
django-perf-review
Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance", "database performance", "Django ORM issues", or audit Django code for performance problems.