hyhmrright/logic-lens
Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, type-contract breaches & async hazards that linters miss. Six skills · Claude Code · Codex CLI · Gemin
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit hyhmrright/logic-lens/.claude ./rig-logic-lens # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit hyhmrright/logic-lens/.claude/skills/bump-version .claude/skills/bump-version $ npx degit hyhmrright/logic-lens/.claude/skills/iterate-skill .claude/skills/iterate-skill $ npx degit hyhmrright/logic-lens/.claude/skills/new-skill .claude/skills/new-skill $ npx degit hyhmrright/logic-lens/.claude/skills/run-iteration-eval .claude/skills/run-iteration-eval $ npx degit hyhmrright/logic-lens/.claude/skills/sync-skill-cache .claude/skills/sync-skill-cache $ npx degit hyhmrright/logic-lens/skills/logic-diff .claude/skills/logic-diff $ npx degit hyhmrright/logic-lens/skills/logic-explain .claude/skills/logic-explain $ npx degit hyhmrright/logic-lens/skills/logic-fix-all .claude/skills/logic-fix-all $ npx degit hyhmrright/logic-lens/skills/logic-health .claude/skills/logic-health $ npx degit hyhmrright/logic-lens/skills/logic-locate .claude/skills/logic-locate $ npx degit hyhmrright/logic-lens/skills/logic-review .claude/skills/logic-review
$ curl -fsSL --create-dirs -o .claude/agents/eval-failure-analyzer.md https://raw.githubusercontent.com/hyhmrright/logic-lens/main/.claude/agents/eval-failure-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/iteration-guard.md https://raw.githubusercontent.com/hyhmrright/logic-lens/main/.claude/agents/iteration-guard.md $ curl -fsSL --create-dirs -o .claude/agents/skill-editor.md https://raw.githubusercontent.com/hyhmrright/logic-lens/main/.claude/agents/skill-editor.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (11)
bump-versioniterate-skillnew-skillrun-iteration-evalsync-skill-cachelogic-difflogic-explainlogic-fix-alllogic-healthlogic-locatelogic-review
Subagents (3)
| eval-failure-analyzer | Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a `skills-workspace/iteration-*` directory or a `benchmarks/runs/*` entry, to cluster failing cases by f |
| iteration-guard model: opus | The verify gate of the Logic-Lens iteration loop. Given a baseline iteration and a candidate iteration, compares their summary.json (overall, logic vs format subscores, per-mode, per-language), accoun |
| skill-editor model: opus | Applies a single, minimal, generalized edit to a Logic-Lens skill (SKILL.md / guide / _shared file) given a concrete failure diagnosis. Use inside the iteration loop after eval-failure-analyzer has pr |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write|MultiEdit | bash "${CLAUDE_PROJECT_DIR}/.claude/hooks/validate-on-edit.sh" |
Slash commands (6)
/logic-diff/logic-explain/logic-fix-all/logic-health/logic-locate/logic-review
Similar rigs
opentabs-dev/opentabs
Browser automation clicks buttons. OpenTabs calls APIs.
Pragmatist 11.6k tok ·
iOfficeAI/AionUi
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up｜Star if you like it!
Pragmatist 2.0k tok ·
hyhmrright/brooks-lint
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
Orchestrator 4.4k tok ·
sami-abdul/claude-predev-setup
A portable system that bootstraps any Claude Code project with production-grade infrastructure: multi-agent pipelines, skills, rules, hooks, and a full-stack development orchestrator inspired by the FullStack-Agent paper.
Orchestrator 1.3k tok ·