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 skills/josephoibrahim/synapse/debug-envnpx skills add JosephOIbrahim/Synapse --skill debug-envgit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWhat 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 | $0.00000 | $0.00321 |
| Opus 5 | $0.00000 | $0.00161 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
debug-env 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 2d 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.
What it actually says
Debug Windows Environment Issue
Parallel diagnostic workflow for permanent environment fixes on Windows 11.
Context
- OS: Windows 11 Pro for Workstations
- Primary terminal: Git Bash
- Elevated commands: PowerShell
- Prefer PowerShell for environment variables (setx), registry, and admin privileges
- Git Bash has escaping issues with setx and UAC interactions
Workflow
Execute these phases — do NOT skip ahead:
Phase 1: Diagnose
- Run
where <tool>andGet-Command <tool>(PowerShell) to find all instances of the target binary - Check for Windows App Execution Aliases (zero-byte stubs in WindowsApps/)
- Inspect PATH ordering
- Identify the exact root cause
- Report findings before proceeding
Phase 2: Fix
- Write a PowerShell script (.ps1) that:
- Fixes the root cause
- Includes error handling for UAC/elevation failures with automatic retry
- Handles Git Bash vs PowerShell escaping differences explicitly
- Save the script to disk for repeatability
- Execute with appropriate elevation
Phase 3: Verify
- Open a NEW shell subprocess and verify the issue is resolved
- Check BOTH PowerShell and Git Bash contexts
- If verification fails, loop back to Phase 2 with the new error
- Do NOT consider resolved until Phase 3 passes in both shells
Arguments
The user should describe the issue after invoking this skill:
/debug-env The claude CLI shows "not recognized" even though it's installed
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.
- 2d ago First seen · 42 lines · 0 tokens per session scan A c369e658467d
debug-env is a skill published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 321 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.
Other skills, from other repositories
dcc-mcp-creator
Infrastructure skill - guide developers and agents through creating or modernizing a DCC-MCP adapter or standalone internal MCP service for Nuke, Blender, 3ds Max, Unreal, ZBrush, Houdini, Maya, and custom studio systems. Use when building server, dispatcher, gateway, packaging, and runtime integration. Not for…
dcc-mcp
Default DCC control skill — connect to and operate live Maya, Blender, Houdini, Photoshop, 3ds Max, Nuke, Unreal, Godot, RenderDoc, Substance 3D, and other DCC apps through structured DCC-MCP tools. Use this skill first for DCC operation and explicit CUA, DCC CUA, dcc-cua, our dcc-cua, or 我们的 dcc-cua requests. These…
dcc-mcp-skills-creator
Infrastructure skill - create, validate, scaffold, and review DCC-MCP skills for the dcc-mcp-core ecosystem. Use when authoring SKILL.md, tools.yaml, scripts, groups, prompts, or skill taxonomy. Not for creating a full DCC-MCP adapter repository - use dcc-mcp-creator.
dcc-mcp-core
Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…
dcc-cua
Project-owned DCC-CUA routing skill for bounded application UI automation. Use this skill whenever the user says dcc-cua, DCC CUA, our dcc-cua, or 我们的 dcc-cua, including browser and other non-DCC UI tasks. These phrases are a hard route to the dcc-mcp project UI Control stack and take precedence over generic…
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…