Is the Foreman Debug skill free?

Yes. The skill itself is free from VisionForge-OU/foreman. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Foreman Debug SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Foreman Debug?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Foreman Debug with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Foreman Debug

Root-cause-first debugging discipline: reproduce, trace to source, fix with a test

by VisionForge-OU · VisionForge-OU/foreman

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4a54e65

On a live failing pytest (KeyError: 'qty', expected total 20.0), the careless no-skill reflex of defaulting the missing key to 0 silenced the crash but returned 10.0 and still failed; following the skill's 'read the assertion completely, trace the bad value to its source' rule pointed to a default of 1, returning 20.0 and a fully green suite. Honest and upfront that it's an obra/superpowers adaptation built to run inside foreman-tdd, so the foreman-test verification hooks are inert on a standalone install.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Foreman Debug does

A headless four-phase debugging loop — root cause, pattern, hypothesis, fix-at-source — that forbids symptom patches and locks every fix with a failing regression test. Triggers when a test, build, or acceptance check is failing, especially on a retry. Designed to run inside a foreman-tdd build session (references foreman-test and FOREMAN-SUMMARY), so standalone installs get the methodology without those hooks.

How to install Foreman Debug

git clone https://github.com/VisionForge-OU/foreman.git
mkdir -p ~/.claude/skills
cd foreman && cp -r src/foreman/skills/foreman-debug ~/.claude/skills/foreman-debug

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Foreman Debug

/foreman-debug Root-cause-first debugging discipline: reproduce, trace to source, fix with a test

It also activates on plain-language prompts like these:

This test is failing with a KeyError, find the actual root cause
Don't just silence this crash, trace the bug back to its source
Fix this failing build and lock it in with a regression test

Frequently asked questions

Is the Foreman Debug skill free?: Yes. The skill itself is free from VisionForge-OU/foreman. SkillProof publishes the install command and an independent test verdict at no cost.
Does Foreman Debug work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. On a live failing pytest (KeyError: 'qty', expected total 20.0), the careless no-skill reflex of defaulting the missing key to 0 silenced the crash but returned 10.0 and still failed; following the skill's 'read the assertion completely, trace the bad value to its source' rule pointed to a default of 1, returning 20.0 and a fully green suite. Honest and upfront that it's an obra/superpowers adaptation built to run inside foreman-tdd, so the foreman-test verification hooks are inert on a standalone install.
What is the Foreman Debug SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Foreman Debug?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Foreman Debug with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.