Synapse: Skill for Claude Code

.claude/skills/deploy/SKILL.md

deploy is a skill for Claude Code from JosephOIbrahim/Synapse. It costs 0 tokens per session (873 once invoked), scanned A, original, MIT.

A deployment procedure for copying SYNAPSE changes from the repository into Houdini's preference files. It also checks whether the installed files match the source files.

In plain words
What is it for?
Use it to preview, install, verify, or uninstall SYNAPSE files, and to report whether Houdini needs a restart.
Why use it?
It reduces the risk of editing or running an outdated deployed copy. It also clarifies when Houdini must be restarted or a panel reopened.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is JosephOIbrahim/Synapse's own configuration. It tells Claude Code how to work on Synapse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Synapse configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/.claude/skills/deploy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

Made for: Claude Code.

Wrote 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.

agentmods badge for deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/josephoibrahim/synapse/deploy/github.svg)](https://agentmods.dev/skills/josephoibrahim/synapse/deploy)
Your own site
<a href="https://agentmods.dev/skills/josephoibrahim/synapse/deploy"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/deploy/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.

agentmods 80×15 button for deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/josephoibrahim/synapse/deploy"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00873
Opus 5.5 $0.00000 $0.00349
Sonnet 5.5 $0.00000 $0.00175
Haiku 4.5 $0.00000 $0.00087

Measured 1mo ago against content hash 70be87f2a363, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deploy 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.

.claude/skills/deploy/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy SYNAPSE

Deploy changes from repo source to Houdini prefs via the installer.

Workflow

  1. Verify source: Confirm all changes are in the repo source ($SYNAPSE_ROOT/houdini/, i.e. <repo>/houdini/) — NOT in deployed copies (houdini22.0/ under your Houdini prefs root)
  2. Run installer: Execute python <repo>/install.py to redeploy shelf, panel, toolbar, and icons
  3. Confirm deployment: Check file timestamps in houdini22.0/ match the source
  4. Report: List what changed and whether Houdini needs to be restarted to pick up the changes

The prefs root is $HOUDINI_USER_PREF_DIR when set; otherwise install.py scans ~/Documents/houdini22.0 (then 21.x, 20.x, 19.x) on Windows. On a host where Documents is OneDrive-redirected the scan misses — set the variable (see below).

Notes

  • Use --dry-run to preview what would be copied without making changes
  • Use --verify to check current deployment matches source
  • Use --uninstall to remove all Synapse files from Houdini prefs
  • Panel changes require closing and reopening the Python Panel tab in Houdini
  • Shelf changes require restarting Houdini

Fresh machine

The build is pinned to Houdini 22.0.400 (python/synapse/recipes/contracts.py::SUPPORTED_BUILD; the committed symbol table python/synapse/cognitive/tools/data/h22_symbol_table.json is stamped 22.0.400). Newer 22.0.x installs are not substitutes: they pass the pytest+PySide6 usability gate and then run against a runtime no symbol table describes.

  1. Install Houdini 22.0.400. It embeds Python 3.13 (python313), so anything added to hython must be cp313: hython -m pip install pytest (PySide6 ships with Houdini). Vendored wheels are checked by python scripts/install_synapse_package.py --verify (H22_ABI = cp313).
  2. Pin the hython. Copy .env.example to .env and keep SYNAPSE_HYTHON=C:/Program Files/Side Effects Software/Houdini 22.0.400/bin/hython.exe. .env is read by synapse.host.auth at Houdini boot only — for shell tools export it too: $env:SYNAPSE_HYTHON = 'C:/Program Files/Side Effects Software/Houdini 22.0.400/bin/hython.exe'. Confirm with python .synapse/hytest.py --which (prints the selected hython; stderr says why).
  3. Prefs dir. $env:HOUDINI_USER_PREF_DIR = '<Documents>/houdini22.0' — explicit, because Documents may be OneDrive-redirected and both install.py and hython otherwise look at the pre-redirect path.
  4. Package file. Either python scripts/install_synapse_package.py (writes a resolved packages/synapse.json into the prefs dir) or $env:HOUDINI_PACKAGE_DIR = '<repo>/packages' to load the repo copy in place. load_package_once guards the double-load if both are set.
  5. Moneta checkout. packages/synapse.json sets MONETA_SRC=$SYNAPSE_ROOT/../Moneta/src and PXR_PLUGINPATH_NAME=$MONETA_SRC/../schema, so clone Moneta beside the SYNAPSE repo (<parent>/Moneta). Headless hython runs that bypass the package need both exported by hand, or MemoryPort reports UNAVAILABLE.
  6. Windows deep paths. git config core.longpaths true before a deep-path clone.
  7. Then the Workflow above: python <repo>/install.py, restart Houdini, run synapse_doctor.

Read the full file on GitHub · 33 lines

Changes

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.

  1. 1mo ago Changed · +14 lines 70be87f2a363
  2. 2mo ago First seen · 19 lines · 0 tokens per session scan A cf1397239058

Subscribe to this mod's changes

deploy is a skill published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 873 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.