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 commands/alwkala/tidyfactor-design/perfgit clone --depth 1 https://github.com/alwkala/tidyfactor-designWrote 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/alwkala/tidyfactor-design/perf)<a href="https://agentmods.dev/commands/alwkala/tidyfactor-design/perf"><img src="https://agentmods.dev/badge/commands/alwkala/tidyfactor-design/perf.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 | $0.00000 | $0.00649 |
| Opus 5 | $0.00000 | $0.00324 |
| Sonnet 5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
perf 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: perf — Asset Performance Budgets & Optimization Check
Runtime entry point for checking asset performance budgets, script preconnects, and load optimization. Part of the Quality & Audit lifecycle phase.
When to use
- Before running
deployor finalizing any prototype - During
auditto verify asset weight compliance - When performance or slow page load is flagged
Asset Performance Budgets (Mechanical Checklist)
Report as a table with actual numbers vs budget limit, not generic pass/fail prose:
| Asset Class | Budget Limit | Rationale |
|---|---|---|
Total Frame Sequence (assets/seq/*.jpg) |
≤ 6.0 MB total (~90–120 frames) | Frame sequence payload on scroll-driven canvas |
| Single JPG Frame | ≤ 60 KB at 1280px wide (q≈80) | Prevents un-scaled frame extraction issues |
| Hero Cutout PNG | ≤ 400 KB (max width 1200px) | Transparent PNGs compress poorly; resize before optimization |
| Brand Logo PNG / SVG | ≤ 40 KB (max width 240px) | Header/footer brand emblem |
| Google Fonts Payload | ≤ 3 families, ≤ 4 weights total | Excess font families delay First Text Paint |
| Total CSS Payload | ≤ 150 KB (gzipped/uncompressed) | Zero per-page CSS constraint enforces shared tokens |
Execution Protocol
- Sum directory sizes:
- Check
assets/anddesign-system/file sizes.
- Check
- Check Font
<link>references:- Verify
<link rel="preconnect" href="https://fonts.googleapis.com">exists. - Verify
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>exists. - Ensure loaded font families match only those referenced in
brand.json.
- Verify
- Verify LCP Optimization:
- Confirm hero image does NOT have
loading="lazy"(violates AI Anti-Pattern Rule #16). - Below-the-fold images MUST use
loading="lazy".
- Confirm hero image does NOT have
- Clean Script Tags:
- Check for dead/duplicate script tags.
Report Output Format
Asset Class Actual Weight Budget Limit Status
------------------------------------------------------------
Hero Cutout PNG 340 KB 400 KB ✅ PASS
Brand Logo SVG 12 KB 40 KB ✅ PASS
Google Fonts 2 families 3 families ✅ PASS
Total CSS 48 KB 150 KB ✅ PASS
LCP Image Eager Yes Yes ✅ PASS
Font Preconnects Present Present ✅ PASS
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.
- 4d ago First seen · 58 lines · 0 tokens per session scan A a4804736e233
perf is a command published in the GitHub repository alwkala/tidyfactor-design (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 649 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 commands, from other repositories
github-issue
Create a GitHub issue from a natural language description.
test
Hello world test command.
coograph-verify
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.
prune
Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.
pr-description
Generate a PR title and description from the current branch diff against main.
conflict
Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.