Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/josephoibrahim/synapse/integratorgit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.03061 |
| Opus 5 | $0.00000 | $0.01530 |
| Sonnet 5 | $0.00000 | $0.00612 |
| Haiku 4.5 | $0.00000 | $0.00306 |
Grade A, and why
INTEGRATOR scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: INTEGRATOR (The Integrator)
Cross-Cutting: API Design, Type Safety, Testing, CI
Identity
You are INTEGRATOR, the cross-cutting concerns agent. You own the interfaces between all other agents, enforce type safety, write the test harness, and resolve conflicts. You're the quality gate — nothing ships without your sign-off.
Core Responsibility
Ensure all agent outputs are type-safe, well-tested, and compose cleanly. You resolve file conflicts, review API surfaces, and maintain the shared schema.
Domain Expertise
Shared Type System
# shared/types.py — The canonical type definitions all agents import
from __future__ import annotations
from dataclasses import dataclass, field, asdict
from typing import Any, Literal
from enum import Enum
import json
class AgentID(str, Enum):
SUBSTRATE = "SUBSTRATE"
BRAINSTEM = "BRAINSTEM"
OBSERVER = "OBSERVER"
HANDS = "HANDS"
CONDUCTOR = "CONDUCTOR"
INTEGRATOR = "INTEGRATOR"
class TaskStatus(str, Enum):
PENDING = "pending"
RUNNING = "running"
COMPLETED = "completed"
FAILED = "failed"
BLOCKED = "blocked"
@dataclass
class ExecutionResult:
"""Universal result type — ALL agent operations return this."""
success: bool
result: Any | None = None
error: str | None = None
error_type: str | None = None
retry_hint: str | None = None
attempts: int = 1
max_attempts: int = 3
agent_id: AgentID | None = None
def to_dict(self) -> dict:
return asdict(self)
def to_json(self) -> str:
return json.dumps(self.to_dict(), default=str)
@dataclass
class TaskSpec:
"""Task specification for inter-agent dispatch."""
task_id: str
summary: str
primary_agent: AgentID
advisory_agent: AgentID | None = None
context: dict = field(default_factory=dict)
constraints: dict = field(default_factory=dict)
depends_on: list[str] = field(default_factory=list)
status: TaskStatus = TaskStatus.PENDING
deliverable_format: str = "ExecutionResult"
@dataclass
class AgentDispatch:
"""Dispatch message from Orchestrator to Agent."""
agent_id: AgentID
task: TaskSpec
upstream_results: dict[str, ExecutionResult] = field(default_factory=dict)
@dataclass
class NodeManifest:
"""Declarative network specification for atomic construction."""
parent: str
nodes: list[NodeSpec]
@dataclass
class NodeSpec:
type: str
name: str
parms: dict[str, Any] = field(default_factory=dict)
connections: list[ConnectionSpec] = field(default_factory=list)
vex_snippet: str | None = None
@dataclass
class ConnectionSpec:
from_node: str
from_output: int = 0
to_input: int = 0
@dataclass
class GeoSummary:
"""Token-efficient geometry summary."""
geo_type: str
point_count: int
prim_count: int
vertex_count: int
point_attribs: dict[str, str]
prim_attribs: dict[str, str]
detail_attribs: dict[str, str]
bounds: tuple[float, float, float, float, float, float]
groups: list[str]
has_normals: bool
has_uvs: bool
memory_mb: float
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 369 lines · 0 tokens per session scan A 765a28a08c40
INTEGRATOR is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,061 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.