tejgokani

Bitecheck — Development skill for Claude Code

Development community

Your agent says the tests pass.

How to install Bitecheck

This entry records only its repository, not the path inside it, so there is no exact command to give. Open tejgokani/bitecheck and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Bitecheck does

Your agent says the tests pass. Do they bite? Deliberately breaks every line your coding agent changed, re-runs your tests, and sends the agent back until its tests catch it. Claude Code, Codex, Gemini, MCP, CI.

Alternatives in Development

Happy Coder — by GrocerPublishAgent - Spawn and control multiple Claude Codes in parallel from your phone or desktop 15.7k ★
L Generate Tests — Generate Tests for Changed Code 3k ★
Zeroshot — Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and not 1.9k ★

README

bitecheck

**Your agent says the tests pass. Do they actually bite?**

bitecheck verifies AI-written code with *execution evidence*, not opinions. It deliberately breaks every line your agent changed, re-runs your tests, and shows you which breaks no test notices. Then it hands those findings back to the agent, so the agent has to fix its tests before it's allowed to finish.

[![ci](https://github.com/tejgokani/bitecheck/actions/workflows/ci.yml/badge.svg)](https://github.com/tejgokani/bitecheck/actions/workflows/ci.yml) ![python](https://img.shields.io/badge/python-3.11%2B-blue) ![deps](https://img.shields.io/badge/runtime%20deps-0-brightgreen) ![license](https://img.shields.io/badge/license-MIT-green)

Works with **Claude Code · Codex · Gemini CLI · any MCP agent · GitHub Actions**. It runs locally, offline and without an LLM, on Python, JS/TS, Go, Rust, Java, Kotlin, Swift, C/C++, C#, PHP and Ruby.

$ git diff --stat
 cart.py      | 11 +++++++++++
 test_cart.py | 11 +++++++++++

$ pytest -q
3 passed in 0.00s

agent: "Added total() with coupon and member discounts. I added comprehensive tests and all tests pass."

$ bitecheck
  ██████████████████░░░░░░  6 of 8 deliberately broken changed lines were caught  (75%, gate 80%)

  ✗ cart.py:8   `/` → `*`               survived: no test failed
  ✗ cart.py:12  `amount *= 0.95` → `pass`  survived: no test failed

  ● goalpost  head pass · base pass · old_tests pass · new_tests FAIL
  ● mutants   6/8 caught (75%)
  ● claims    3 claim(s): 1 contradicted
      ERROR CLAIM_CONTRADICTED: the agent claimed the tests are thorough, but only 6 of 8
            deliberately broken changed lines were caught by the tests (75%)
  verdict: FAIL

That's real output from [`examples/demo.sh`](examples/demo.sh), trimmed. The suite was green and coverage would say 100%. But halving a price is never checked (the test asserts `> 0`), and the member discount could be deleted without a single test noticin