Plugin Claude Code
GraphSmith: lifecycle hooks that keep every Claude Code session and every Task-spawned subagent grounded in the GraphSmith multi-agent discipline from the moment they start.
3 2d ago A
tokens not measured
original MIT
graphsmith
02Cursor rule Cursor
Build and fix reliable multi-agent AI workflows: crash-safe steps, idempotent retries, deterministic routing. Use for agent, pipeline, orchestration, or automation work, or when an existing automation loses state, loops, duplicates work, or fabricates results.
3 2d ago A 52 tokens
original MIT
Instructions file GitHub Copilot
Instructions for SathiaAI/graphsmith, covering graphsmith, mode detection (do this first, silently), phase 0 — ground (knosky), phase 1 — blueprint (mandatory gate before code) and phase 2 — build.
3 2d ago A 2,392 tokens
original MIT
Instructions file CodexOpenCode
Instructions for SathiaAI/graphsmith, covering graphsmith, mode detection (do this first, silently), phase 0 — ground (knosky), phase 1 — blueprint (mandatory gate before code) and phase 2 — build.
3 2d ago A 2,394 tokens
copy · 97% MIT
graphsmith
05Skill Claude CodeCodex
Build and fix reliable multi-agent AI workflows for any skill level, from first-time builders to senior engineers. ALWAYS use this skill when the user asks to "build an agent", "automate" a task or workflow, wants "AI to do X for me", describes a multi-step job, mentions agents, bots, pipelines, swarms, or…
3 2d ago A 204 tokens
original MIT
graphsmith
06Skill Claude CodeCodex
Build and fix reliable multi-agent AI workflows for any skill level, from first-time builders to senior engineers. ALWAYS use this skill when the user asks to "build an agent", "automate" a task or workflow, wants "AI to do X for me", describes a multi-step job, mentions agents, bots, pipelines, swarms, or…
3 2d ago A 204 tokens
copy · 100% MIT
graphsmith
07Plugin Claude Code
SessionStart and SubagentStart hooks that inject the GraphSmith multi-agent discipline (from the repo's canonical SKILL.md) into context for every session and every Task-spawned subagent from the moment it starts.
3 2d ago A
tokens not measured
original MIT
graphsmith
08Skill Claude CodeCodex
Build and fix reliable multi-agent AI workflows for any skill level, from first-time builders to senior engineers. ALWAYS use this skill when the user asks to "build an agent", "automate" a task or workflow, wants "AI to do X for me", describes a multi-step job, mentions agents, bots, pipelines, swarms, or…
3 2d ago A 204 tokens
copy · 100% MIT
Instructions file CodexOpenCode
Instructions for SathiaAI/adversarial-review, covering agent instructions, if you are an agent working on this repository itself and install locations.
2 yesterday A 634 tokens
original MIT
Skill Claude CodeCodex
Independent adversarial review and deterministic release gating for code changes, using a multi-model reviewer panel over OpenRouter (or any OpenAI-compatible router, or an MCP transport like Composio). Use whenever the user asks for an adversarial review, red-team review, multi-model review, independent review…
2 yesterday A 125 tokens
original MIT