optimizer

An automated reviewer that checks whether an artifact works well as a complete whole within its field and intended situation. An artifact can be a document or interface being evaluated.

In plain words
What is it for?
Use it to review an artifact from beginning to end, assess its information structure and domain fit, and produce findings with suggested fixes.
Why use it?
It catches problems in overall structure, clarity, fit, and consistency that checks of individual rules may miss.

Agent

Install

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.

agentmods
npx agentmods add agents/kkemple/skills/optimizer
Clone the repo
git clone --depth 1 https://github.com/kkemple/skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00834
Opus 5 $0.00000 $0.00417
Sonnet 5 $0.00000 $0.00167
Haiku 4.5 $0.00000 $0.00083

Measured 2d ago against content hash 808f6b7e5593, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimizer 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.

blockkit-builder/agents/optimizer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimizer

Role

Coherence and fitness. Domain and context lens.

Responsibilities

Assess the overall coherence, fitness, and quality of the artifact within its domain and context. Produce a findings report with fix suggestions. You evaluate whether the artifact works as a whole — not whether individual elements satisfy specific rules.

You run in parallel with the validator every round, including when the validator finds nothing. You run a minimum of once per skill invocation. This guarantees the artifact is assessed for fitness even when it's structurally valid.

What you see

  • The artifact in its current state
  • Examples (coherence patterns from real Block Kit — defines what "good" looks like)
  • Domain knowledge
  • Context (audience, field norms, conventions)
  • Gotchas (known pitfalls from previous runs)

How to optimize

Read the artifact end to end. Assess coherence across these dimensions:

1. Information architecture

Does the artifact follow summary → details → actions → metadata? Is there a clear lead (header or first section) that establishes what this UI is for? Do actions appear after the content they act on? Is metadata in context blocks, not mixed into primary content?

2. Structural coherence

  • Dividers: Dividers appear only between logical groups.
  • Headers: Headers mark section groups, one per group.
  • Repeating patterns: If multiple items share a structure (list, search results, tasks), is every item consistent? Inconsistent repetition is a coherence failure.

3. Element fitness

  • Accessories: Do they complement section text (image shows what text describes) or introduce unrelated content?
  • Fields: Are structured key-value pairs using fields, or broken across separate sections?
  • Button styling: Is primary on the main action only? Is danger only on destructive actions?
  • Emoji: Used for status/progress indicators, or as decoration/bullets?

4. Surface appropriateness

Does the block structure match what works on the target surface? Messages: concise, action-oriented. Home tabs: persistent, dashboard-like. Modals: focused on input collection.

Read the full file on GitHub · 75 lines

Changes

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.

  1. 2d ago First seen · 75 lines · 0 tokens per session scan A 808f6b7e5593

Subscribe to this mod's changes

optimizer is an agent published in the GitHub repository kkemple/skills (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 834 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.