By sancovp
SDNA (Sanctuary DNA) - Gnostic agent workflow DSL with skills for chain development
⭐ 0 stars • 🕑 Updated 2026-07-10
📦 Auto-published from the monorepo • CHANGELOG • sancovp/sdna
Gnostic agent workflow composition for Claude Agent SDK.
Ariadne (threading) + Poimandres (generation) = SDNA spiral
pip install sdna-agent-sdk
from sdna import ariadne, human, inject_file, sdnac, sdna_flow, HermesConfig
# 1. Build Ariadne thread (context prep)
thread = ariadne('my-thread',
inject_file('spec.md', 'spec'),
human('Approve spec?', 'approval'), # Pauses for human input
)
# 2. Create HermesConfig (the message)
config = HermesConfig(
name="generator",
system_prompt="You are a code generator...",
)
# 3. Combine into SDNAC
unit = sdnac('generate-code', thread, config)
# 4. Execute
result = await unit.execute({'initial': 'context'})
| Component | Role | What It Does |
|---|---|---|
| Ariadne | Threader | Context manipulation: inject, weave, dovetail, human input |
| Poimandres | Divine Mind | Generation moment - takes config, runs agent, returns output |
| HermesConfig | The Message | Runner configuration Ariadne sends to Poimandres |
Is this continuous improvement / optimization loop?
├── YES → SDNA^F (SDNAFlowchain)
│ Optimizer + target pairs. Meta-optimization.
│
└── NO → Are you composing multiple agent units in sequence?
├── YES → SDNAF (SDNAFlow)
│ Flow of SDNACs. Sequential execution.
│
└── NO → SDNAC
Single unit: AriadneChain → HermesConfig → Poimandres executes
from sdna import (
ariadne, # Create chain
human, # Human input stop step
inject_file, # Inject file contents
inject_func, # Inject function result
inject_literal, # Inject literal value
inject_env, # Inject env variable
weave, # Context surgery between sessions
)
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub sancovp/sdna --plugin sdnaAutopoiesis Plugin - Self-maintaining promise loops for honest AI work
A compiler-compiler for cognition: invent a notation, gate it so the model can't malform it, compile it into a loadable skill, compose and organize them. Ships the meta-APE capability skills (make-prompt, make-persona, big-generator, persona-generator, forge-attention-chain, forge-cor, forge-skillchain, construct-language) — one per CC/*CC build-function — plus bandit-chain-system, glyphsteer, glyphsteer-dense and the Self-Interpreter MCP. Built on agent-prompt-engineering (APE, the prompt engine) over pydantic-stack-core, with the *CC (accc/corcc/sccc) made FROM chaincompiler. Requires the Python packages: ./install.sh, then `pip install fastmcp` for the MCP.
CodeNose - Configurable code smell detection for LLMs. Sniffs out duplicate logic, architecture violations, missing logging, and other blind spots.
Instantiate a TWI Jobworld — AI-powered company with agents that run themselves. Enable this plugin and a CEO agent spawns, ready to bootstrap your company.
Program agent teams for any coding agent — the programmable, provider-agnostic version of Claude Code Teams. Compose agents with a tiny DSL (>> and |), loop/contest/evolve topologies, and game-worlds. CAVE = Coding Agent Virtualization Environment.
A single-skill package for generating harness blueprints for agentic systems.
Workflow orchestration system for coordinating multiple AI agents (Claude, Codex, Gemini, OpenCode). Enables complex multi-model automation.
Hot-reloadable versioned prompts with easy tools for prompt engineering, chain workflows, quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'
Agent Script workflows end to end: the ultracodex runner skill (execute multi-agent workflows on the OpenAI Codex CLI), the model-agnostic agent-script-authoring skill, and a seven-shape example gallery.
Enterprise AI agent orchestration plugin with 150+ commands, 74+ specialized agents, SPARC methodology, swarm coordination, GitHub integration, and neural training capabilities
Run Claude Code dynamic-workflow scripts on a local Codex App Server — fan out Codex/GPT agents with the agent/parallel/pipeline DSL, sessionful steerable workers, supervised fleets (--multi), live viewers, and run analytics.