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 instructions/josephoibrahim/synapse/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.svg" alt="Measured on agentmods" 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 | $0.09295 | $0.09295 |
| Opus 5 | $0.04647 | $0.04647 |
| Sonnet 5 | $0.01859 | $0.01859 |
| Haiku 4.5 | $0.00929 | $0.00929 |
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 4d 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 — 490 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 v5.57.0 · Python 3.13 · 128 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(external-MCP) → the Lossless Execution Bridge: undo-wrapped, main-thread-marshalled, consent-gated, scene-hashed, with anIntegrityBlock+ fidelity verdict per op. The audited path./synapse(live WS) →server.handlersdirectly: RBAC-gated, main-thread-marshalled (run_on_main), 30s slow-op timeout, undo-wrapped only partially (⚠ drift, verified 2026-07-10; updated 2026-08-15 W5-UNDO: usd/material/cops/batch/execute handlers wrap inhou.undos.group, and as of W5-UNDO thehandlers_node.pycreate/connect/delete handlers wrap too — grouping only, not rollback (see next paragraph). As of W5-UNDOB the two remaining tracked holes also wrap:set_parm(handlers.py:_handle_set_parm, around itsparm.set/parm_tuple.set) andset_keyframe(handlers_render.py:_handle_set_keyframe, aroundparm.setKeyframe) — same grouping-only semantics, no rollback. Scope caveat: live mutating handlers beyond this tracked set are still not audited here, so this is not a claim that every live op wraps.server/integrity_envelope.py's honesty docstring (~L19-28) was synced by W5-UNDOB to record these handlers as wrapping inline (grouping only); it no longer brands this §1 claim "doc drift" for the create/connect/delete node handlers. Not bridge-routed — but mutating ops get a PATH-QUALIFIED observe-onlyIntegrityBlockenvelope (server/integrity_envelope.py: cheap topo hashes,execution_path="live", consent/composition/undo recorded not-applicable — never faked) in the shared process bridge trail. Still noHumanGateconsent escalation, 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.
- 4d ago First seen · 490 lines · 9,295 tokens per session scan A 4f07239564f5
Synapse CLAUDE.md is an instructions file published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 13d ago), licensed MIT. It adds 9,295 tokens to every session, about $0.0465 per session on Opus 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
dcc-mcp-core CLAUDE.md
Claude Code instructions for dcc-mcp/dcc-mcp-core, covering claude.md — dcc-mcp-core, read order, mandatory dcc workflow and build & test.
dcc-mcp-houdini AGENTS.md
AGENTS.md instructions for dcc-mcp/dcc-mcp-houdini, covering agents.md — dcc-mcp-houdini, agent control path, cli availability and updates, quick start (inside houdini) and skills-first workflow.
dcc-mcp-houdini CLAUDE.md
Claude Code instructions for dcc-mcp/dcc-mcp-houdini, covering what this project does, claude desktop configuration, progressive loading — important for claude, claude-specific tips and quick test prompts.
dcc-mcp-houdini GEMINI.md
Gemini CLI instructions for dcc-mcp/dcc-mcp-houdini, covering gemini.md — google gemini / vertex ai integration guide, what this project does, integration setup, gemini-specific tips and quick test prompts.
dcc-mcp-core AGENTS.md
AGENTS.md instructions for dcc-mcp/dcc-mcp-core, covering agents.md — dcc-mcp-core, ⚡ critical: skills-first philosophy, 🚀 agent entry strategy: cli+rest (default) vs ide mcp, response language and command efficiency.
dcc-mcp-core GEMINI.md
Gemini CLI instructions for dcc-mcp/dcc-mcp-core, covering gemini.md — dcc-mcp-core, read order, mandatory dcc workflow and build & test.