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/batteryshark/rekit/cc-buildnpx skills add batteryshark/rekit --skill cc-buildgit clone --depth 1 https://github.com/batteryshark/rekitWrote 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/batteryshark/rekit/cc-build)<a href="https://agentmods.dev/skills/batteryshark/rekit/cc-build"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/cc-build.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 | $0.00096 | $0.00552 |
| Opus 5 | $0.00048 | $0.00276 |
| Sonnet 5 | $0.00019 | $0.00110 |
| Haiku 4.5 | $0.00010 | $0.00055 |
Grade A, and why
cc-build 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 4d 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.
What it actually says
C/C++ Compiler (clang)
🔨 Construct tier — this skill produces an artifact, it doesn't read a sample.
Purpose
cc-build creates the native artifacts RE work needs: PoCs, test harnesses, decompiler
fixtures, and shared libraries. It compiles but does not run the result. Use
exec-observe for an executable or emulate-code for shellcode and object bytes.
What it does
Thin, honest wrapper over clang (falls back to cc/gcc): picks a compiler, builds
the argv, runs it, and reports the artifact path/size plus the compiler diagnostics.
--emit exe|obj|asm|ir— link an executable, a.o, assembly (.s), or LLVM IR (.ll, clang only).asm/irare great for seeing what the compiler generates.- Cross-compile with
--target <triple>and/or--arch. --std,--opt,--shared,--static, and--cflags "…"for anything else.
Prerequisites
- A C compiler —
clang(macOS:xcode-select --install; Linux: install clang/LLVM) orgcc. Checked flexibly (clang || cc || gcc); absent → honest install hint.
Safety
executes_input: no — the produced binary is never run. Caveat: compiling untrusted
source still invokes a compiler, so it's tier 1, not 0. The usual input is your own
trusted PoC source.
Usage
rekit run cc-build poc.c --out poc # build an exe
rekit run cc-build shellcode_stub.c --emit obj # → .o for emulate-code
rekit run cc-build foo.c --emit asm --opt 0 # see the codegen
rekit run cc-build mod.c --shared --target aarch64-linux-gnu # cross-compiled .so
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.
- 4d ago First seen · 45 lines · 96 tokens per session scan A 5882d2941b4c
cc-build is a skill published in the GitHub repository batteryshark/rekit (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 96 tokens to every session and 552 once invoked, about $0.0005 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
new-cpp-lint
Create a new C++ lint rule, test it, run it across the codebase, and selectively apply fixes. Usage - /new-cpp-lint.
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
ax-cpp-agent-memory-skills
Use when writing C++ code with axllm for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-cpp-signature
Use when writing C++ code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.