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 zhinkgit/embeddedskills --skill gccgit clone --depth 1 https://github.com/zhinkgit/embeddedskillsWrote 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/zhinkgit/embeddedskills/gcc)<a href="https://agentmods.dev/skills/zhinkgit/embeddedskills/gcc"><img src="https://agentmods.dev/badge/skills/zhinkgit/embeddedskills/gcc/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/zhinkgit/embeddedskills/gcc"><img src="https://agentmods.dev/badge/skills/zhinkgit/embeddedskills/gcc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00162 | $0.01760 |
| Opus 5.5 | $0.00065 | $0.00704 |
| Sonnet 5.5 | $0.00032 | $0.00352 |
| Haiku 4.5 | $0.00016 | $0.00176 |
Grade A, and why
gcc 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCC 嵌入式工程构建
本 skill 提供基于 CMake + arm-none-eabi-gcc 的嵌入式工程发现、preset 枚举、配置生成、增量编译、全量重建、清理和 ELF 大小分析能力。
范围说明：当前仅支持 CMake 型 GCC 嵌入式工程，不覆盖纯 Makefile 工程。
配置
环境级配置（skill/config.json）
skill 目录下的 config.json 包含环境级配置，首次使用前确认 cmake_exe 路径正确：
{
"cmake_exe": "cmake",
"toolchain_prefix": "arm-none-eabi-",
"toolchain_path": "",
"operation_mode": 1
}
cmake_exe：cmake 可执行文件路径，默认从 PATH 查找toolchain_prefix：工具链前缀，默认arm-none-eabi-，用于定位 size 等工具toolchain_path：工具链 bin 目录，为空时从 PATH 查找operation_mode：1直接执行 /2输出风险摘要但不阻塞 /3执行前确认
工程级配置（workspace/.embeddedskills/config.json）
工程级共享配置统一保存在工作区的 .embeddedskills/config.json 中：
{
"gcc": {
"project": "",
"preset": "",
"log_dir": ".embeddedskills/build"
}
}
project：默认工程路径（相对 workspace），构建成功后会自动更新preset：默认 CMake preset 名称，构建成功后会自动更新log_dir：构建日志输出目录，默认.embeddedskills/build
参数解析优先级
参数解析顺序（从高到低）：
- CLI 显式参数
- 环境级配置（skill/config.json）
- 工程级配置（.embeddedskills/config.json）
- state.json（上次构建记录）
- 搜索/询问
冲突解决规则：同一参数存在多个来源时，以序号最小的来源为准；高序号来源仅在低序号来源未提供该参数时生效。例如：CLI 已指定 --preset Debug，则忽略 state.json 中记录的上次 preset。
子命令
| 子命令 | 用途 | 风险 |
|---|---|---|
scan |
搜索当前目录下的 CMake 嵌入式工程 | 低 |
presets |
列出 CMakePresets.json 中的 configure/build preset | 低 |
configure |
执行 cmake --preset 生成构建系统 |
中 |
build |
增量编译 cmake --build |
中 |
rebuild |
清理后全量重建 | 中 |
clean |
清理构建目录 | 高 |
size |
分析 ELF 文件大小（text/data/bss 和内存使用） | 低 |
执行流程
- 读取
config.json，确认cmake_exe路径有效 - 未提供有效子命令时默认执行
scan - 未提供工程路径时先执行
scan搜索工程 - 发现多个工程或多个 preset 时列出选项让用户选择，绝不自动猜测
configure/build/rebuild/clean按operation_mode决定是否需要确认build前自动检测是否已 configure，未配置时提示先执行 configurebuild/rebuild成功后返回elf_file，供jlink/openocd继续使用size默认分析最近一次构建产物的 .elf 文件
脚本调用
skill 目录下有三个 Python 脚本，使用标准库实现，无额外依赖。
gcc_project.py — 工程扫描与 preset 枚举
# 扫描工程
python <skill-dir>/scripts/gcc_project.py scan --root <搜索目录> --json
# 列出 preset
python <skill-dir>/scripts/gcc_project.py presets --project <工程目录> --json
What ships with it
6 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.
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 · 166 lines · 162 tokens per session scan A d8908c80113c
gcc is a skill published in the GitHub repository zhinkgit/embeddedskills (756 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 1,760 once invoked, about $0.0006 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
mastra-api
Interact with Mastra development server API for debugging agents, viewing conversation threads, listing/inspecting tools and workflows, accessing observability data, and managing Mastra resources. Use when working with Mastra agents and need to inspect runtime state, debug agent errors, view thread history, see…
d3k
Use when the user asks to use d3k, run/dev/test/debug a web project with d3k, or reproduce a browser issue. Own the runtime: reuse or background-start d3k non-interactively, wait for readiness, use its project-stable managed Chrome profile, and inspect unified browser/server evidence.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
devtools-bidirectional
Two-way event patterns between devtools panel and application. App-to-devtools observation, devtools-to-app commands, time-travel debugging with snapshots and revert. structuredClone for snapshot safety, distinct event suffixes for observation vs commands, serializable payloads only.
devtools-instrumentation
Analyze library codebase for critical architecture and debugging points, add strategic event emissions. Identify middleware boundaries, state transitions, lifecycle hooks. Consolidate events (1 not 15), debounce high-frequency updates, DRY shared payload fields, guard emit() for production. Transparent server/client…
deck-repro
Reproduce agent-deck bugs from an issue, transcript excerpt, or description in an isolated environment, and prove fixes with the same reproduction and a regression test. Use for a concrete agent-deck issue or candidate, verifying a fix, preparing a contributor bug-fix PR, or when deck-retro passes a candidate. Broad…