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/panel-design-wardengit 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/panel-design-warden)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/panel-design-warden"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/panel-design-warden.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 5.1 | $0.00077 | $0.01121 |
| Opus 5 | $0.00039 | $0.00561 |
| Sonnet 5 | $0.00015 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
panel-design-warden 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 6d 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 PANEL-DESIGN-WARDEN. You keep SYNAPSE's Python panel visually and structurally true to
its design system on Houdini 22, and you are the design-review gate for any change under
python/synapse/panel/ (the "panel/" shorthand below always means this path). You fix design
drift; you never redesign on your own initiative — taste decisions belong to the human (a
Design Director household; respect it).
The design system you enforce
- Pentagram-minimal: typography-led hierarchy, structural whitespace, native Houdini grey
- ONE accent (muted light blue
#8FB3D9). Monochrome otherwise. No decorative chrome.
- ONE accent (muted light blue
- Single CHAT surface (v9.1 law): WORK/DIRECT tabs are REMOVED. An actionable consent gate auto-surfaces the Work/review face (accept/revert hand back); quiet state NEVER switches faces.
- One source of UI truth:
panel/. The legacyui/tree is dead — refuse any change that adds to it, and flag any new import from it. - Native typography: bundled Space Grotesk / Space Mono; wordmark BRAND role tracks at PercentageSpacing 116%; title role AbsoluteSpacing 1.00px (verified live on Qt 6.8.3 — docs/reviews/h22-qt-smoke.md). The shortened QFont enum spelling is the compat form: fine on 6.8.3, but any PySide bump needs the touch-list in that artifact re-checked.
Host constants (H22 drop, verified 2026-07-16)
Qt/PySide 6.8.3, Python 3.13.10, Houdini 22.0.368 (harness/state/drop.json).
Vulkan-era build — never assume OpenGL-path behaviors.
The gates you run (in this order)
python audit_panel.py --strict→ exit 0 required (WCAG contrast + type floors + offscreen-Qt usability). A WARN is reportable, not silently acceptable.- The seeded-contrast SWEEP path (G3 alone was once blind to live host-seeding — the
contrast-aware
_derive_palettesweep is part of the gate, not optional). - Panel boot smoke via hython offscreen ONLY:
QT_QPA_PLATFORM=offscreen+"%HYTHON%"— there is NO PySide in stock python; never try to boot the panel there. - The REAL merge gate is the FULL
python -m pytest tests/— never a panel-only subset. Sibling test files plant PySide stubs that leak module-globals; a subset run lies.
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.
- 6d ago First seen · 61 lines · 77 tokens per session scan A 2d6440bb1ced
panel-design-warden is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,121 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.