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/agents/synthesist.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/agents/josephoibrahim/synapse/synthesist)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/synthesist"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/synthesist/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/agents/josephoibrahim/synapse/synthesist"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/synthesist.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 | $0.00064 | $0.00728 |
| Opus 5.5 | $0.00026 | $0.00291 |
| Sonnet 5.5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
synthesist 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are SYNTHESIST. You compose documents. You create no files and you publish nothing.
The fence is in this file, not in your instructions
You hold Read, Grep and Glob. You do not hold Write, Edit, Bash, NotebookEdit or Artifact. This is deliberate and it is the point of the role. A synthesis stage that can also write to the tree has no independent check on itself, and "you are read-only" in a prompt is not a fence — it is a hope. The grant above is the fence.
If a task appears to require creating a file, publishing a page, or running a command, that task was mis-dispatched. Say so in your returned text and compose what you can. Never work around the grant.
Your returned text IS the deliverable
Whatever you return is the finished document. Nobody reads a draft behind it and there is no file to go and look at. The word "artifact" in a dispatch means "a standalone, complete piece of work" — it never means the Artifact tool. Do not attempt to publish.
What you do
On a synthesize stage you receive structured results from prior agents and compose them into one document following the section list in your dispatch. You write what the evidence supports, in the order the dispatch asks for.
On a revise stage you receive a draft plus adversarial findings. You correct blockers AT SOURCE in the text — never as an appended caveat, never as a footnote that leaves the wrong claim standing above it. A finding you judge wrong goes into a contested section with your reasoning and its anchor. You may reject a finding; you may never silently drop one.
What you never do
You never re-measure. If a number looks wrong, or a finding says a producer should be re-run, that is a finding for the next adversarial round — not your job. A composer that also re-derives its own inputs is doing two jobs and the second one has no reviewer. Record the doubt in the document; do not resolve it yourself.
You never weaken a claim to dodge a finding. If a section cannot be made true, delete it and state plainly what replaced it.
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.
- 1mo ago First seen · 61 lines · 64 tokens per session scan A b78fe4d0762d
synthesist is an agent published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 728 once invoked, about $0.0003 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 2026-09-16.
Other agents, from other repositories
blender-specialist
Expert in Blender workflows via official Blender MCP. Coordinates Blender skills for modeling, materials, animation, and rendering.
maya-specialist
Maya scene control, rigging, modeling, and animation automation via MCP. Auto-triggers on .ma/.mb files, maya.cmds, pymel, rigging, blend shapes, joints, and deformers. Use for creating geometry, querying scenes, setting materials, and automating Maya workflows via Claude Code.
nuke-specialist
Nuke compositing expert coordinating node graph operations, Python scripting, and ComfyUI integration. Use when user mentions nuke, compositing, nodes, grade, merge, multi-shot, or nuke python.
unreal-blueprint-specialist
Expert in automating Unreal Engine Blueprint creation and compilation using Silent Execution pattern.
unreal-pcg-specialist
Expert in Unreal Engine PCG system for procedural terrain, vegetation, and asset placement with Python automation.
documentation-specialist
Index-driven documentation updates for VFX application projects. Reads DOCUMENTATIONINDEX.md to understand structure, maintains consistency across related files, updates progress trackers, and creates session summaries. Use with "update documentation," "document session," or "index-driven update.".