agentrigs
+ submit rig
~ / rigs / techygarg / lattice

techygarg/lattice

Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

↗ GitHub ★ 155 mit updated 3mo ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.5k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit techygarg/lattice/.claude ./rig-lattice  # 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 techygarg/lattice/skills/architecture-compass .claude/skills/architecture-compass
$ npx degit techygarg/lattice/skills/architecture-refiner .claude/skills/architecture-refiner
$ npx degit techygarg/lattice/skills/architecture .claude/skills/architecture
$ npx degit techygarg/lattice/skills/bug-fix .claude/skills/bug-fix
$ npx degit techygarg/lattice/skills/clean-code-refiner .claude/skills/clean-code-refiner
$ npx degit techygarg/lattice/skills/clean-code .claude/skills/clean-code
$ npx degit techygarg/lattice/skills/code-forge .claude/skills/code-forge
$ npx degit techygarg/lattice/skills/collaborative-judgment .claude/skills/collaborative-judgment
$ npx degit techygarg/lattice/skills/context-anchoring .claude/skills/context-anchoring
$ npx degit techygarg/lattice/skills/ddd-refiner .claude/skills/ddd-refiner
$ npx degit techygarg/lattice/skills/design-blueprint .claude/skills/design-blueprint
$ npx degit techygarg/lattice/skills/design-first .claude/skills/design-first
$ npx degit techygarg/lattice/skills/domain-driven-design .claude/skills/domain-driven-design
$ npx degit techygarg/lattice/skills/knowledge-priming-refiner .claude/skills/knowledge-priming-refiner
$ npx degit techygarg/lattice/skills/knowledge-priming .claude/skills/knowledge-priming
$ npx degit techygarg/lattice/skills/language-idioms-refiner .claude/skills/language-idioms-refiner
$ npx degit techygarg/lattice/skills/lattice-init .claude/skills/lattice-init
$ npx degit techygarg/lattice/skills/learning-harvest .claude/skills/learning-harvest
$ npx degit techygarg/lattice/skills/refactor-safely .claude/skills/refactor-safely
$ npx degit techygarg/lattice/skills/refiners-update .claude/skills/refiners-update
$ npx degit techygarg/lattice/skills/requirement-forge-refiner .claude/skills/requirement-forge-refiner
$ npx degit techygarg/lattice/skills/requirement-forge .claude/skills/requirement-forge
$ npx degit techygarg/lattice/skills/requirement-quality .claude/skills/requirement-quality
$ npx degit techygarg/lattice/skills/review-refiner .claude/skills/review-refiner
$ npx degit techygarg/lattice/skills/review .claude/skills/review
$ npx degit techygarg/lattice/skills/secure-coding .claude/skills/secure-coding
$ npx degit techygarg/lattice/skills/test-quality .claude/skills/test-quality
$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/techygarg/lattice/main/agents/verifier.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 (27)

architecture-compassarchitecture-refinerarchitecturebug-fixclean-code-refinerclean-codecode-forgecollaborative-judgmentcontext-anchoringddd-refinerdesign-blueprintdesign-firstdomain-driven-designknowledge-priming-refinerknowledge-priminglanguage-idioms-refinerlattice-initlearning-harvestrefactor-safelyrefiners-updaterequirement-forge-refinerrequirement-forgerequirement-qualityreview-refinerreviewsecure-codingtest-quality

Subagents (1)

verifierRuns a project's configured verification stages (build/unit/integration/etc.) from `.lattice/verification.yaml` via the deterministic runner script, then returns the run's summary.json verbatim. Invok

Plugins (1)

skill-creator@claude-plugins-official

Similar rigs

95gabor/agentic-workflow
🔨 Agentic workflow template
★ 2 project CodexCursor 10 skills 3mo ago
Skill Collector 4.5k tok ·
tammai/ai-sdlc
Claude Code plugin for vibe coding on the AI-native SDLC playbook: intent → design → spec → plan → verify → review → ship. Runs on a Claude subscription, with opinionated stacks (Nuxt/Next + Cloudflare, Go + Postgres, Flutter, Tauri) and de
★ 0 project Claude Code 16 skills 13 agents 3d ago
Orchestrator 3.2k tok ·
owainlewis/blueprint
The best agent skills in the world for software development.
★ 411 project Claude CodeCodex 11 skills 6d ago
Skill Collector 2.5k tok ·
decebals/claude-code-java
Reusable AI development infrastructure for Java projects, optimized for Claude Code
★ 749 project Claude Code 18 skills 1mo ago
Skill Collector 1.2k tok ·
copied ✓