skill-eval-improve

skill-eval-improve is a skill for Claude Code, Codex from Arenukvern/mcp_flutter. It costs 61 tokens per session (2,411 once invoked), scanned A, original, MIT.

A quality-improvement workflow for existing Agent Skills, which are instruction packages that guide coding agents. It measures a skill, makes limited edits, and checks it again.

In plain words
What is it for?
Evaluating skill descriptions and procedures, reducing their token cost, checking regressions, and applying bounded improvements.
Why use it?
It helps find skills that trigger incorrectly, produce weak results, or contain unnecessary instructions without relying on untested changes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: paths in frontmatter, but also reads ~/.codex or $CODEX_HOME. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

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 skills/arenukvern/mcp_flutter/skill-eval-improve
Any agent
npx skills add Arenukvern/mcp_flutter --skill skill-eval-improve
Clone the repo
git clone --depth 1 https://github.com/Arenukvern/mcp_flutter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skill-eval-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/skill-eval-improve.svg)](https://agentmods.dev/skills/arenukvern/mcp_flutter/skill-eval-improve)
Your own site
<a href="https://agentmods.dev/skills/arenukvern/mcp_flutter/skill-eval-improve"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/skill-eval-improve.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,411 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 5.1 $0.00061 $0.02411
Opus 5 $0.00030 $0.01205
Sonnet 5 $0.00012 $0.00482
Haiku 4.5 $0.00006 $0.00241

Measured 6d ago against content hash 95275b22371b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-eval-improve 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/skill-eval-improve/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill eval & improve

Improve skills measurably: baseline → measure → bounded edit → re-validate. Combine local tooling, Codex plugin-eval (when installed), and research-backed loops (SkillOpt).

When to use

  • Skill triggers wrong or never loads (description routing)
  • Bloated SKILL.md, high token cost, weak outcomes
  • After adding a new procedure—need regression checks
  • Porting patterns from product MCP / plugin-eval research into Skill Steward skills

When not to use

  • Bulk repo validation — e.g. “validate every skill in this repo” → pnpm run validate only (skill-authoring-lifecycle for audit); do not start benchmark or SkillOpt loops.
  • Automated SkillOpt / cluster training — Skill Steward documents a manual bounded-edit loop; no overnight optimizer pipeline.
  • Creating a new skill — use skill-authoring-lifecycle first; eval-improve applies after a skill exists.

Cursor scope (optional): activate when editing under skills/** or scripts/validate-skills.mjs.

Mixture of experts (evaluation stack)

Layer Expert Tool / method Cost
0 — Gate Lint pnpm run validate, skill-authoring-lifecycle seconds
0b — Rules Routing/docs SSOT pnpm run eval (T1 behavior-critical YAML cases) seconds
1 — Static Structure Codex plugin-eval analyze (if available) seconds
2 — Human Behavior 3–5 prompts with/without skill minutes
3 — Measured Usage plugin-eval benchmark + measurement-plan minutes–hours
4 — Evolve Text optimization SkillOpt-style bounded edits + held-out gate hours
5 — Navigate Telemetry / dogfood Current steward benchmark scenarios on compact traces seconds

Use the cheapest layer that answers the question. Do not skip layer 0.

Layer 0 — Skill Steward validator (always)

Read the full file on GitHub · 203 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. 6d ago First seen · 203 lines · 61 tokens per session scan A 95275b22371b

Subscribe to this mod's changes

skill-eval-improve is a skill published in the GitHub repository Arenukvern/mcp_flutter (373 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 2,411 once invoked, about $0.0003 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 2026-08-30.