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-distill)<a href="https://agentmods.dev/commands/perniemann/pncore/pn-distill"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-distill/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-distill"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-distill.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 | $0.00041 | $0.00716 |
| Opus 5 | $0.00020 | $0.00358 |
| Sonnet 5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
pn-distill 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 8d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-distill
Start every response with: [pn-command] 🔺
Advanced (palette-hidden). Not in the
/slash palette. Invoked by/pn-visual-tweakor/pn-polish, or directly viaget_command("pn-distill").
Radical simplification. For when too much has accumulated — features, decoration, copy, navigation — and the core value is buried. Remove until only what earns its place remains.
When to Use
- Landing page isn't converting — too much competing for attention
- Dashboard is cluttered — users don't know where to look
- Component has grown complex — needs to be redesigned from intent
- Before a redesign: strip the current version to understand what's essential
- "We added a lot of stuff, let's clean it up"
The Principle
Every element should answer: "If I removed this, would the user lose something essential?"
If no: remove it.
Flow
1. Intent First
Before removing anything: what is this page/component/flow trying to accomplish?
- Primary action: what should the user do?
- Primary message: what should the user understand?
- Primary emotion: how should the user feel after using it?
Everything that doesn't serve one of these three is a candidate for removal.
2. Audit for Removal
Content:
- Text that restates what's already shown elsewhere
- Section introductions that say what the heading already says
- Feature lists where 20% get 80% of attention — cut the 80%
- Supporting stats or proof that duplicate the primary proof
Visual:
- Decorative elements that don't reinforce brand or message
- Icons used as filler, not communication
- Background patterns or textures serving no atmospheric purpose
- Shadow, border, and background stacking (element inside bordered card inside shadowed section)
Navigation:
- Menu items users never click
- Secondary CTAs competing with the primary
- Multi-level navigation for a small surface area
Interaction:
- Animations with no functional role
- Hover states that reveal nothing useful
- Modals for simple confirmations
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.
- 8d ago First seen · 88 lines · 41 tokens per session scan A 88fc63eb089b
pn-distill is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 716 once invoked, about $0.0002 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 commands, from other repositories
t800-start
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
t800-loop
A semi-manual workflow for reviewing the results of a previous development run and preparing a queue of fixes. HITL means a human reviews or approves the queued work before fixes are applied in batches.
t800-audit
A command for auditing a Cursor setup, including its rules, skills, commands, agents, and plugins. It identifies which parts are useful and which consume unnecessary context, meaning the instructions an AI reads before working.
t800-onboard
A command for newcomers that explains what is installed in Cursor globally and in the current project, plus what the T-800 team can do.
t800-cloud-hub
A command for setting up a Cloud Hub and its client automation package, including instructions, a data format, and a test report.
t800-doctor
A command that runs a scripts-only health report for a T-800 or target plugin setup. It reports the version, profile, memory location, state, item counts, always-applied items, and recent audits.