Selftest — Testing skill for Claude Code
Run the hardmode self-test — the real shipped hooks against planted failure modes in a throwaway sandbox, plus the hooks.json wiring check.
How to install Selftest
Installs to ~/.claude/skills/blyatiful1-hardmode-selftest/SKILL.md
mkdir -p ~/.claude/skills/blyatiful1-hardmode-selftest && curl -fsSL https://raw.githubusercontent.com/blyatiful1/hardmode/HEAD/commands/selftest.md -o ~/.claude/skills/blyatiful1-hardmode-selftest/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Selftest does
description: Run the hardmode self-test — the real shipped hooks against planted failure modes in a throwaway sandbox, plus the hooks.json wiring check. Run it after a Claude Code update allowed-tools: Bash(python3:*)
Self-test output:
!`python3 "${CLAUDE_PLUGIN_ROOT}/tools/demo.py"`
Report the final `demo: N/N` line. If any scenario printed `[FAIL]`, quote each failing line verbatim and say which guard is no longer firing — that guard's rule is advisory only until it is fixed
Alternatives in Testing
- Claude Codepro — by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen 1.6k ★
- Fixtests — Systematic test failure analysis and remediation 849 ★
- Integration Test — Test elixir plugin post-edit hooks by walking through fixture projects in test/integration/fixtures/ 174 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Cfn Pseudo
SPARC Pseudocode phase. Trace logic, enumerate branches, find failure paths, verify branch coverage BEFORE wri
Claudemd Update
Sync ~/.claude/CLAUDE.md with the plugin-cache shipped spec. Shows diff summary; user chooses apply-all or can
Wsq Setup
Install or update the WSQ courseware toolchain (skills, commands, the courseware-qa agent, the push scripts an
Sp.Autonomous
Fully autonomous project builder - analyzes current project, generates missing skills/agents/hooks, tests them
AI Tester
End-to-end behavioral testing skills, bare system prompts, and any agent runtime — run real scenarios in an is
Haritrail
Watch Claude Code work through your codebase live: every file it reads, edits and creates, every command and t
Related Agents
Failure Mode Reviewer
Finds self-inflicted failure modes the implementation missed — the ways future-you, an AI collaborator, or a h
Bm Domain Researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domai
Gsd Domain Researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domai