← Browse
sams-agentic-workflow
sam-ash-cy ★ 2
This Claude Code plugin implements a tiered, evidence-driven agentic workflow that routes coding tasks by risk level (trivial, standard, complex, critical), enforces guardrails via hooks, and requires verification checks before a task can complete. It works with a companion CLI tool (`saw`) to record metrics, block unsafe operations, and generate improvement proposals from repeated failures.
Install
> /plugin marketplace add sam-ash-cy/sams-agentic-workflow
> /plugin install sams-agentic-workflow
What it's made of
6 agents · 5 skills · 8 hooks
- Commands
- 0
- Agents
- 6
- Skills
- 5
- MCP servers
- 0
- Hooks
- 8 · PostToolUse, PreToolUse, SessionStart, Stop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
saw- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (sam-ash-cy).