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/lanesket/llm.log/normalizenpx skills add lanesket/llm.log --skill normalizegit clone --depth 1 https://github.com/lanesket/llm.logWhat 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 | $0.00012 | $0.00801 |
| Opus 5 | $0.00006 | $0.00400 |
| Sonnet 5 | $0.00002 | $0.00160 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
normalize 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.
This is a copy
95% identical to normalize — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze and redesign the feature to perfectly match our design system standards, aesthetics, and established patterns.
MANDATORY PREPARATION
Use the frontend-design skill — it contains design principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no design context exists yet, you MUST run teach-impeccable first.
Plan
Before making changes, deeply understand the context:
-
Discover the design system: Search for design system documentation, UI guidelines, component libraries, or style guides (grep for "design system", "ui guide", "style guide", etc.). Study it thoroughly until you understand:
- Core design principles and aesthetic direction
- Target audience and personas
- Component patterns and conventions
- Design tokens (colors, typography, spacing)
CRITICAL: If something isn't clear, ask. Don't guess at design system principles.
-
Analyze the current feature: Assess what works and what doesn't:
- Where does it deviate from design system patterns?
- Which inconsistencies are cosmetic vs. functional?
- What's the root cause—missing tokens, one-off implementations, or conceptual misalignment?
-
Create a normalization plan: Define specific changes that will align the feature with the design system:
- Which components can be replaced with design system equivalents?
- Which styles need to use design tokens instead of hard-coded values?
- How can UX patterns match established user flows?
IMPORTANT: Great design is effective design. Prioritize UX consistency and usability over visual polish alone. Think through the best possible experience for your use case and personas first.
Execute
Systematically address all inconsistencies across these dimensions:
- Typography: Use design system fonts, sizes, weights, and line heights. Replace hard-coded values with typographic tokens or classes.
- Color & Theme: Apply design system color tokens. Remove one-off color choices that break the palette.
- Spacing & Layout: Use spacing tokens (margins, padding, gaps). Align with grid systems and layout patterns used elsewhere.
- Components: Replace custom implementations with design system components. Ensure props and variants match established patterns.
- Motion & Interaction: Match animation timing, easing, and interaction patterns to other features.
- Responsive Behavior: Ensure breakpoints and responsive patterns align with design system standards.
- Accessibility: Verify contrast ratios, focus states, ARIA labels match design system requirements.
- Progressive Disclosure: Match information hierarchy and complexity management to established patterns.
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 · 73 lines · 12 tokens per session scan A 3c85740beedf
normalize is a skill published in the GitHub repository lanesket/llm.log (22 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 801 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to normalize, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
gmgn-contract-dd
Contract due-diligence score for one token address — contract safety, holder structure and price action combined into a single 0-100 composite, capped by GMGN's own rug label, where every deduction names the field it read and an absent field is never a passing check. Use when the user wants one verdict number rather…
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
browser-use
Drive agentglass's built-in browser — the one already signed in to the sites this project uses. Use when a task needs a page behind a login (a dashboard, a ticket, a staging app), when a URL fetched with curl comes back signed out or JavaScript-rendered, or when the user asks you to look at, click through, or…
go-rig
Use this skill when building, reviewing, or refactoring Go code that must follow strict design discipline — ATDD/TDD workflow, explicit dependency injection, package-boundary discipline, and structured code review. Complements CLAUDE.md by focusing on process and design judgment rather than version-specific Go…
cost-tracking
Use when metering and capping AI or cloud app spend — tokens read from the response usage object, priced off a dated rate table, ledgered per user/tenant/feature, with alerts and a hard cap before the bill. NOT cash runway (that is finance-ops), NOT cost-per-unit margin (that is unit-economics), NOT booking the spend…