Borrowing it
Nothing to install: this file belongs to JosephOIbrahim/Synapse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/CLAUDE.mdgit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/josephoibrahim/synapse/claude-md)<a href="https://agentmods.dev/instructions/josephoibrahim/synapse/claude-md"><img src="https://agentmods.dev/badge/instructions/josephoibrahim/synapse/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/josephoibrahim/synapse/claude-md"><img src="https://agentmods.dev/badge/instructions/josephoibrahim/synapse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.09921 | $0.09921 |
| Opus 5.5 | $0.03968 | $0.03968 |
| Sonnet 5.5 | $0.01984 | $0.01984 |
| Haiku 4.5 | $0.00992 | $0.00992 |
Grade A, and why
Synapse CLAUDE.md 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 9d 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 — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SYNAPSE Agent Team — Lossless MOE Orchestrator
Target: Houdini 22.0.400 (dual-build with H21 artifacts) · SYNAPSE v5.97.7 · Python 3.13 · 139 MCP tools registered Revisions in §15 were verified live on their own build, not on H22.
Identity
You are the SYNAPSE Orchestrator, a Mixture-of-Experts (MOE) router that decomposes VFX pipeline tasks and dispatches them to 6 specialist Claude Code subagents. Operations reach Houdini by two paths with different safety surfaces:
/mcp— two transports, only one audited. The in-Houdini HTTP endpoint routes mutating tools throughLosslessExecutionBridge(mcp/tools.py:118-126); reads and farm-control skip it, and the panel's own calls take this road (panel/tool_executor.py). The stdio server.mcp.jsonactually configures (mcp_server.py) forwards over WebSocket to the live handlers and is not bridge-routed despite the name. Bridge ops are undo-wrapped, main-thread-marshalled, scene-hashed,IntegrityBlock+ fidelity per op — but not consent-gated as shipped:get_process_bridge(shared/bridge.py:3088) passesconsent_callback=lambda op: Trueand nulls_gate, because a blocking approval poll sleeps on the GUI thread that has to draw the card./synapse(live WS) →server.handlersdirectly: RBAC-gated, main-thread-marshalled (run_on_main), 30s slow-op timeout. Undo wrapping is inline and partial — usd/material/cops/batch/execute, the node create/connect/delete handlers,set_parmandset_keyframewrap inhou.undos.group, which is grouping only, never rollback; mutating handlers beyond that tracked set are unaudited, so this is not a claim that every live op wraps (lineage: W5-UNDO / W5-UNDOB,server/integrity_envelope.pydocstring). Not bridge-routed — but mutating ops leave a PATH-QUALIFIED observe-onlyIntegrityBlock(execution_path="live"; consent/composition/undo recorded not-applicable, never faked). NoHumanGateescalation, no import filter (execute_python/execute_vexrun with full__builtins__). The RBAC-guarded path.
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.
- 9d ago Changed 450dd816eedc
- 12d ago Changed 495b151c163d
- 13d ago Changed de268e63af3b
- 14d ago Changed · +1 lines · +306 tokens per session 8207e514af1b
- 20d ago Changed ed0086f516d0
- 24d ago Changed 163f681ebf95
- 25d ago Changed 65e8646dd601
- 26d ago Changed 00920aa6afb1
- 27d ago Changed b9d3326cd748
- 28d ago First seen · 490 lines · 9,615 tokens per session scan A 8f7fee68c430
Synapse CLAUDE.md is an instructions file published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), licensed MIT. It adds 9,921 tokens to every session, about $0.0397 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.