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.
git clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/commands/perniemann/pncore/pn-audit-design-tokens)<a href="https://agentmods.dev/commands/perniemann/pncore/pn-audit-design-tokens"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-design-tokens/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/commands/perniemann/pncore/pn-audit-design-tokens"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-design-tokens.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 | $0.00042 | $0.00580 |
| Opus 5.5 | $0.00017 | $0.00232 |
| Sonnet 5.5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
pn-audit-design-tokens 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-audit-design-tokens
Start every response with: [pn-command] 🔺
Advanced (palette-hidden). Not in the
/slash palette. Invoked by the/pn-frontend-auditumbrella, or directly viaget_command("pn-audit-design-tokens").
Focused design-token pass: audit CSS custom property (or design system token) coverage, naming conventions, dark-mode completeness, and hardcoded value elimination. No typography changes (use pn-audit-typography) — tokens only.
Flow
1. Context
Check .pncore-stack.md for CSS framework and token approach (Tailwind / CSS variables / styled-system / etc.). Scope: "All styles or specific files/components?"
2. Audit
Token coverage:
- Are all colors defined as CSS custom properties (
--color-*or equivalent)? - Are spacing values from a defined set of tokens?
- Are font families and sizes tokenized?
- Are border-radii, shadow definitions, and z-index values tokenized?
Hardcoded values:
- Any
color: #hexorbackground: rgb(...)not using a variable? - Any
margin: 24pxorpadding: 12pxnot using a spacing token? - Any
font-size: 14pxnot using a type token?
Naming conventions:
- Semantic tokens (e.g.
--color-text-primary) separate from primitive tokens (--color-gray-700)? - Consistent naming format (kebab-case, BEM, or design system standard)?
Dark mode:
- All semantic color tokens have dark-mode overrides (via
prefers-color-schemeor.darkclass)? - No semantic tokens that reference light-mode primitives directly without override?
Token file structure:
- Tokens defined in one canonical file (not scattered across component files)?
- No duplicate variable declarations?
Output: numbered issues table (location | issue | severity | suggested fix). Save to docs/audits/.
Gate: Present issues for triage. Apply after confirmation.
3. Fix
Apply in order: consolidate token file → replace hardcoded values → add dark-mode overrides → rename inconsistent tokens.
4. Summary
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 · 62 lines · 42 tokens per session scan A d924af150ae3
pn-audit-design-tokens is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 580 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
quality-check
Execute a comprehensive quality gate check (lint, test, build, format) before allowing code to merge.
t800-fix
A command for making a narrow, predefined fix to existing agents, skills, commands, rules, or hooks. A fix-pack is a file listing the exact changes to make.
t-800-factory
A command that delegates creation or integration of a subagent to the T-800 Factory. It passes the proposed role, category, permissions, callers, and existing registry information to that factory.
implement
Use to turn a spec or user request into working, tested code.
t-800-health
bash scripts/health-check.sh.
run_tests
Use the text the user typed after the command name as the request for this command.