bind-cpp

A tool for generating Python, Lua, or JavaScript interfaces to C++ classes by inspecting C++ header files. It uses mirror_bridge so developers do not have to write the binding code by hand.

In plain words
What is it for?
Use it to generate bindings for a directory of C++ headers, add include paths, inspect generation errors, and check whether bindings have drifted after header changes.
Why use it?
It reduces the manual code needed to make a C++ library callable from another programming language and can identify unsupported member types.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/franciscothiesen/mirror_bridge/bind-cpp
Any agent
npx skills add FranciscoThiesen/mirror_bridge --skill bind-cpp
Clone the repo
git clone --depth 1 https://github.com/FranciscoThiesen/mirror_bridge

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.00799
Opus 5 $0.00038 $0.00400
Sonnet 5 $0.00015 $0.00160
Haiku 4.5 $0.00008 $0.00080

Measured 2d ago against content hash 3092b2356526, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bind-cpp 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 2d 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.

integrations/claude-code/skills/bind-cpp/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binding C++ with mirror_bridge

mirror_bridge auto-discovers every struct/class in a directory of C++ headers and compiles a binding module. Nobody writes binding code: not the user, not you.

Procedure

  1. Locate the toolchain. Try in order:

    • mirror_bridge version (pip install: pip install mirror-bridge)
    • The mirror_bridge MCP tools, if connected (generate_bindings, doctor, check_binding_drift)
    • docker run --rm -v "$PWD:/workspace" -w /workspace ghcr.io/franciscothiesen/mirror_bridge:latest bash tools/mirror_bridge ... (inside a mirror_bridge checkout)

    If none works, suggest pip install mirror-bridge (requires Docker) and stop.

  2. Generate. Always use --json and parse stdout (it is exactly one JSON object; progress goes to stderr):

    mirror_bridge generate <header_dir> --module <name> --lang python --json
    

    --lang choices: python, lua, js, all. Extra include roots: -I <dir>.

  3. On failure, read errors[].suggestion — it names the fix. The common loop:

    • "member type has no converter": open the named header, find the offending member (handles, mutexes, raw pointers to user types, function pointers), and annotate it:

      #include "python/mirror_bridge_annotations.hpp"
      using mirror_bridge::exclude;
      
      struct Engine {
          double speed;                      // bound
          [[=exclude{}]] void* impl_handle;  // skipped
      };
      

      Use // MIRROR_BRIDGE_SKIP on the line directly above a class to skip the whole class, or // MIRROR_BRIDGE_SKIP_FILE to skip a file. Re-run generate. Repeat until "status": "ok".

    • Environment problems (compiler, headers): run mirror_bridge doctor --json and apply the hint of each failed check.

  4. Verify. Import and exercise the module; the .so/.node is listed in the JSON outputs:

    PYTHONPATH=build python3 -c "import <name>; print(dir(<name>))"
    

Read the full file on GitHub · 73 lines

Changes

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.

  1. 2d ago First seen · 73 lines · 76 tokens per session scan A 3092b2356526

Subscribe to this mod's changes

bind-cpp is a skill published in the GitHub repository FranciscoThiesen/mirror_bridge (86 stars, last pushed 6d ago), licensed Apache-2.0. It adds 76 tokens to every session and 799 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens