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 instructions/mattgodbolt/specbolt/claude-mdgit clone --depth 1 https://github.com/mattgodbolt/specboltWrote 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/instructions/mattgodbolt/specbolt/claude-md)<a href="https://agentmods.dev/instructions/mattgodbolt/specbolt/claude-md"><img src="https://agentmods.dev/badge/instructions/mattgodbolt/specbolt/claude-md.svg" alt="Measured on agentmods" 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 | $0.00782 | $0.00782 |
| Opus 5 | $0.00391 | $0.00391 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
specbolt CLAUDE.md 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 5d 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.
mkdir -p ~/opt && curl -fsSL https://s3.amazonaws.com/compiler-explorer/opt/gcc-16.2.0.tar.xz | tar Jxf - -C ~/opt How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build
Requires clang-20+ (for C++26 modules + libc++), CMake 3.30+, Ninja, SDL2, readline.
Presets live in CMakePresets.json. The common ones:
cmake --preset debug # Debug, no modules — works with clang or gcc
cmake --preset debug-modules # Debug with C++ modules (needs clang + libc++)
cmake --preset release # RelWithDebInfo, no modules (runs zexdoc tests)
cmake --preset debug-reflection # Debug with C++26 reflection (needs gcc 16+)
cmake --build --preset debug
ctest --preset debug
Pick the compiler with CC=… CXX=… or by setting CMAKE_CXX_COMPILER in a local CMakeUserPresets.json (gitignored) that inherits from one of the public presets.
The zexdoc regression tests are intentionally skipped in Debug (too slow); they run in RelWithDebInfo.
Run: ./build/debug/sdl/specbolt_sdl
C++26 reflection
Reflection (P2996) needs gcc 16+; no clang release implements it yet, and the WASI build is on clang, so anything reflective must be optional. cmake/reflection.cmake probes for it and exposes:
opt::reflection— link against it to get-freflectionand theSPECBOLT_REFLECTIONdefine. Guard reflective code on that macro, or exclude the target in CMake withif (SPECBOLT_HAS_REFLECTION).SPECBOLT_REFLECTIONcache variable —AUTO(default, use if available),ON(require it; configure fails otherwise),OFF.
No distro packages gcc 16, so grab a compiler-explorer build — the same thing CI uses:
mkdir -p ~/opt && curl -fsSL https://s3.amazonaws.com/compiler-explorer/opt/gcc-16.2.0.tar.xz | tar Jxf - -C ~/opt
CC=~/opt/gcc-16.2.0/bin/gcc CXX=~/opt/gcc-16.2.0/bin/g++ cmake --preset debug-reflection
Reflection works inside module interface units on gcc 16 — including template for in a module purview, and exported templates that reflect on their own parameters and get instantiated in importing TUs. The reflection presets still set SPECBOLT_MODULES=OFF to keep the reflection and modules axes separable; flip it in a CMakeUserPresets.json to build both together.
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.
- 5d ago First seen · 55 lines · 782 tokens per session scan A 2f81d159ac3a
specbolt CLAUDE.md is an instructions file published in the GitHub repository mattgodbolt/specbolt (41 stars, last pushed 15d ago), licensed BSD-3-Clause. It adds 782 tokens to every session, about $0.0039 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
xiaozhi-esp32 AGENTS.md
AGENTS.md instructions for 78/xiaozhi-esp32, covering agents.md, project, architecture, required rules and boards and configuration.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
monkey AGENTS.md
Instructions for monkey/monkey, covering agents, repository map, main runtime flow, build and verification and commit style used in this repository.
nim_duilib CLAUDE.md
Instructions for rhett-lee/nim_duilib, covering nimduilib - 跨平台 c++ ui 库, 项目概述, 项目结构, 开发模式（xml + c++） and xml 布局文件.
PDF-Writer CLAUDE.md
Instructions for galkahana/PDF-Writer, covering claude code context - pdf-writer development guide, project overview, coding standards discovered, project structure and key components.
foundry-local cpp-formatting.instructions.md
Use when writing or modifying C++ source/header files. Covers vertical whitespace conventions for readability.