By sancovp
SDNA (Sanctuary DNA) - Gnostic agent workflow DSL with skills for chain development
โญ 0 stars โข ๐ Updated 2026-06-23
๐ฆ Auto-published from the monorepo โข CHANGELOG โข 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?
โโโ YES โ SDNA^F (SDNAFlowchain)
โ Optimizer + target pairs. Meta-optimization.
โ
โโโ NO โ Are you composing multiple agent units in sequence?
โโโ YES โ SDNAF (SDNAFlow)
โ Flow of SDNACs. Sequential execution.
โ
โโโ NO โ SDNAC
Single unit: AriadneChain โ HermesConfig โ 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.
Autopoiesis Plugin - Self-maintaining promise loops for honest AI work
CodeNose - Configurable code smell detection for LLMs. Sniffs out duplicate logic, architecture violations, missing logging, and other blind spots.
Instantiate a TWI Jobworld โ AI-powered company with agents that run themselves. Enable this plugin and a CEO agent spawns, ready to bootstrap your company.
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. Bundles the capability skills (bandit-chain-system, glyphsteer, glyphsteer-dense, report-missed-skill) and the Self-Interpreter MCP. Requires the Python packages: ./install.sh, then `pip install fastmcp` for the MCP.
The doc-mirror claude system: a 1:1 documentation mirror of any codebase, maintained by an invariant doc-mirror STATE MACHINE (per-module doc(m), 6 context/ index files, fork-on-change, no random documents). Bundles doc-mirror-boot (entry + core-loop prime + router), the doc-mirror-{init,seework,change,prompts} state-skills, doc-mirror-install (the host-setup WIZARD), ship-a-plugin (the build+distribute dev-flow), doc-mirror (THE LAW), and make-ai-operating-system (the architect for new systems of this class); the brainhook work-loop + session-start + transition-guard + readonly-guard hooks (plugin-native via CLAUDE_PLUGIN_ROOT); the journal/projects/vision/plan/tracker/commit/cursor + docmirror-search CLI tools; and the doc-mirror law + behavior rules.
npx claudepluginhub sancovp/sdna --plugin sdnaA single-skill package for generating harness blueprints for agentic systems.
11 agents, 35 skills, 18 commands, 9 hooks โ spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
Enterprise AI agent orchestration plugin with 150+ commands, 74+ specialized agents, SPARC methodology, swarm coordination, GitHub integration, and neural training capabilities
Multi-agent workflow orchestration via YAML. Ships the conductor skill so the assistant can validate, run, debug, and author workflow files for the conductor CLI.
maenifold-enabled product team
Multi-agent orchestration framework for Claude Code. Routes tasks to specialized Haiku/Sonnet subagents while Opus orchestrates โ inspired by speculative decoding. Includes 10 specialized heads, environment preflight checks, and ~50% API cost reduction.