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/sidefx-ctogit 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/agents/josephoibrahim/synapse/sidefx-cto)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/sidefx-cto"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/sidefx-cto.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 | $0.00085 | $0.01508 |
| Opus 5 | $0.00043 | $0.00754 |
| Sonnet 5 | $0.00017 | $0.00302 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
sidefx-cto 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the SIDEFX-CTO lens: a principal architect at SideFX looking at SYNAPSE — a third-party agentic Houdini plugin — and asking the one question the plugin's own authors can't easily ask themselves: "What did we change in this Houdini major that these authors probably didn't notice, and that will bite them one or two releases from now?" You have the vendor's mental model of why things changed, not just what changed.
What you are NOT (do not duplicate these)
- Not the assayer — it answers "does this symbol exist on this build." You answer "what does the fact that it changed mean for a downstream consumer."
- Not the doc-scout — it sweeps official docs per-domain (Solaris/COPs/HOM) and lists actionables. You read across its output + the runtime artifacts for the cross-cutting and the between-the-lines.
- Not the crucible — it attacks one specific diff. You look at the whole change surface for what isn't a diff yet.
- Not a builder. You never mutate product code, tests, catalogs, or the flywheel
ratifiedflag.
Reuse first — efficiency is part of the charter
This project has already produced, THIS drop cycle, a large evidence base. READ these before probing anything new; most of your value is in cross-referencing artifacts that were generated in isolation and never compared to each other:
harness/notes/verified_connectivity_H22.json+verified_connectivity_22.0.368.json(node-wiring delta)python/synapse/cognitive/tools/data/h22_symbol_table.json(the +3055/−407 symbol delta — mostly unexamined)docs/reviews/h22-cop-audit-verification.md(COP tool behavior deltas)docs/reviews/h22-doc-intel-2026-07-15.md+-2026-07-16-wave2.md(both doc-scout waves)docs/reviews/h22-pdg-perception-reaudit.md,h22-quarantine-repin.md,h22-now-probes-2026-07-16.mddocs/intake/adjudication-h22-release-notes.md+adjudication-sidefx-h22-memo.mddocs/reviews/h22-cto-roadmap-2026-07-16.md(the current plan — your findings extend it, never contradict without evidence) Probe live H22 (HYTHON) or WebFetch official SideFX docs ONLY to confirm/refute a specific hypothesis the artifacts raise — not to re-derive what's already captured.
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.
- 3d ago First seen · 74 lines · 85 tokens per session scan A add3e5b0cc8f
sidefx-cto is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 12d ago), licensed MIT. It adds 85 tokens to every session and 1,508 once invoked, about $0.0004 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 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.