Ai Agent Solution Architect
Commands, skills, hooks, and templates for Solution Architects using Claude Code, Cursor, and Codex.
Install
$ agentstack add mcp-casper7995-ai-agent-solution-architect ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/mcp-casper7995-ai-agent-solution-architect) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AI Agent Solution Architect
Cross-platform commands, skills, hooks, and templates for Solution Architects using AI coding agents — Claude Code, Cursor, and Codex.
Battle-tested workflows extracted from daily enterprise delivery: architecture review, CI repair, merge conflict resolution, agent orchestration, and code quality passes.
Platform support
| Asset | Claude Code | Cursor | Codex | |-------|-------------|--------|-------| | Commands / prompts | ~/.claude/commands/ | ~/.cursor/commands/ | Skills in ~/.codex/skills/ (see [INSTALL.md](INSTALL.md)) | | Skills | ~/.claude/skills/ | ~/.cursor/skills/ | ~/.codex/skills/ | | Hooks | ~/.claude/hooks/ + settings.json | Cursor hooks (optional) | Not supported | | Project memory | CLAUDE.md | AGENTS.md / rules | AGENTS.md |
Most assets are plain Markdown and shell scripts. Copy the paths that match your agent; see [INSTALL.md](INSTALL.md) for per-platform steps.
What's inside
Commands (8)
| Command | What it does | |---------|--------------| | /feature-dev | Guided feature development: explore → clarify → design → implement → review | | /deslop | Clean AI-generated code patterns (over-commenting, defensive slop, premature abstractions) | | /fix-ci | Read failing CI logs, diagnose, apply minimal fix | | /loop-on-ci | Iterate fix → commit → push → check until CI is green (max 5 rounds) | | /fix-merge-conflicts | Resolve conflicts intelligently and validate the build | | /copilot-mode-start | Collaborative mode with architecture review and decision checkpoints | | /copilot-mode-end | Exit copilot mode, return to autonomous execution | | /weekly-review | Summarize commits, PRs, and impact for standup or retro |
Skills (2)
| Skill | What it does | |-------|-------------| | agent-team-orchestration | Parallel sub-agent orchestration with quality gates and /deslop integration | | claude-api-specialist | Claude API / SDK / Agent SDK expert that fetches latest docs at runtime |
Hooks (4) — Claude Code
| Hook | Trigger | What it does | |------|---------|--------------| | auto-format.sh | After Edit/Write | ruff on .py, prettier on .ts/.tsx/.js/.jsx | | capture-session.sh | Session start | Saves session ID for easy session forking | | pre-commit-check.sh | Before git commit | Blocks commit if staged .py imports untracked modules | | post-plan-sync.sh | After plan mode | Sync plan to project .claude/plans/ |
Templates
| Template | What it does | |----------|-------------| | settings.example.json | Permission allow/deny lists + hook configuration (Claude Code) | | CLAUDE.md.template | Project memory starting point for Claude Code | | AGENTS.md.template | Project memory starting point for Cursor / Codex | | gitignore.claude | Lines to add to .gitignore for agent-local files |
Quick start
git clone https://github.com/casper7995/ai-agent-solution-architect.git
cd ai-agent-solution-architectThen follow [INSTALL.md](INSTALL.md) for your agent (Claude Code, Cursor, or Codex).
Requirements
- At least one of: Claude Code CLI, Cursor, or Codex CLI
- For CI commands:
ghCLI authenticated with GitHub - For hooks (Claude Code):
jq; optionalruffandprettier - For auto-format hook:
ruff(Python) and/orprettier(JS/TS) — skips gracefully if missing
Recommended plugins (Claude Code)
This kit pairs well with official Claude Code plugins: commit-commands, code-review, superpowers, claude-md-management. See [docs/recommended-plugins.md](docs/recommended-plugins.md).
For Cursor, browse the Marketplace and user skills under Settings → Rules, Skills, Subagents. Author profile: cursor.com/@casper.
Connect
Casper Hsieh | GitHub | Cursor | LinkedIn
Philosophy
Not a framework — a curated kit you copy into agent config directories. Fork it, adapt paths per platform, delete what you do not need.
Every command, skill, and hook here was extracted from production Solution Architect workflows.
License
MIT
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: casper7995
- Source: casper7995/ai-agent-solution-architect
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.