Synapse: Skill for Claude Code

.claude/skills/solaris-harden/SKILL.md

solaris-harden is a skill for Claude Code from JosephOIbrahim/Synapse. It costs 0 tokens per session (1,307 once invoked), scanned A, original, MIT.

A step-by-step process for hardening Solaris network wiring and node recognition. Solaris is Houdini's system for building and composing USD scenes, while LOP nodes are the nodes that work with those scenes.

In plain words
What is it for?
Use it when extending, auditing, or preparing changes to the Solaris builder, its graph assembly, or its wiring and node-recognition logic.
Why use it?
It helps catch regressions that appear only when features are combined, rebuilt, or used more than once. The process includes checks against the real Houdini build and stops at defined review points.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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/solaris-harden/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 solaris-harden

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/josephoibrahim/synapse/solaris-harden"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/solaris-harden.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 1,307 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 $0.01307
Opus 5 $0.00000 $0.00654
Sonnet 5 $0.00000 $0.00261
Haiku 4.5 $0.00000 $0.00131

Measured 10d ago against content hash 341057b5f971, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

solaris-harden 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 10d 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/solaris-harden/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harden SYNAPSE Solaris Wiring

Coordinated production-hardening pipeline for SYNAPSE's Solaris (LOP) network wiring and node recognition on the pinned Houdini build. Drives ground-truth → design → integrate → adversarial seam-gate → live-verify → land, halting at every human gate. Use when hardening, extending, or auditing the Solaris builder, or before landing any change to build_graph / assemble_chain / the wiring + recognition authorities.

Why this exists (read once)

Across the hardening effort this pipeline was assembled by hand four times, and every time the isolated work went green and an independent adversary caught a real composed regression — twice a data-corruption bug that only appeared on the SECOND action (the rebuild, the second network, the interaction with an existing feature). This skill codifies that loop so the lesson is structural, not rediscovered. The load-bearing stage is D (the seam-gate); it is never skipped.

The primitives it coordinates (mostly already in the repo)

  • Ground truth: scripts/harvest_lop_catalog.py, host/introspect_connectivity.py (live catalog producers) → the committed *_catalog_*.json / lop_solaris_knowledge_*.json.
  • Gates (harness/verify/checks.py): entry = connectivity_catalog_fresh, lop_catalog_fresh, phantom_clean; exit = wiring_conformance, validator_catches_miswire, validator_lop_conformance, suite_baseline (ratchet).
  • Agents: cartographer (read-only mapper), prospector (candidates), sidefx-cto (vendor lens), and seam-hunter (the adversarial composition gate — this harness's own agent).
  • Live verify: scripts/run_live_probes.py (the probe battery + negative-control discipline).

The pipeline

Announce the arc before starting: dense build register through D; sea-level teach-down after land.

ENTRY GATE — refuse on stale truth (un-skippable). Confirm you are on the pinned build (harness/state/drop.json:houdini_build; synapse_ping / houdini_scene_info for a live session). Run the freshness gates; if the live catalog is stale or a phantom leaked, STOP and regenerate (harvest_lop_catalog.py) before any design. A change grounded on stale truth is the #1 failure class here.

Read the full file on GitHub · 82 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. 10d ago First seen · 82 lines · 0 tokens per session scan A 341057b5f971

Subscribe to this mod's changes

solaris-harden is a skill published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,307 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.