self-eval

self-eval is a skill for Claude Code from Morningstar202604/awesome-skillkit. It costs 51 tokens per session (1,934 once invoked), scanned A, original, Apache-2.0.

A structured way to assess the quality of AI-produced work using separate ratings for task difficulty and execution quality. It includes a required argument for both a higher and a lower rating, plus saved scores for comparison over time.

In plain words
What is it for?
Use it after a coding task, review, or work session to evaluate the task’s ambition and the quality of its execution.
Why use it?
It reduces the tendency to rate every task similarly and makes the reasoning behind a score easier to challenge. Past scores can reveal repeated overrating.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Claude Code.

Good fit Use it after a coding task, review, or work session to evaluate the task’s ambition and the quality of its execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/morningstar202604/awesome-skillkit/self-eval
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.

Any agent
npx skills add Morningstar202604/awesome-skillkit --skill self-eval
Clone the repo
git clone --depth 1 https://github.com/Morningstar202604/awesome-skillkit

Made for: Claude Code.

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 self-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/self-eval.svg)](https://agentmods.dev/skills/morningstar202604/awesome-skillkit/self-eval)
Your own site
<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/self-eval"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/self-eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00051 $0.01934
Opus 5 $0.00026 $0.00967
Sonnet 5 $0.00010 $0.00387
Haiku 4.5 $0.00005 $0.00193

Measured 7d ago against content hash 0b829818fd15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

self-eval 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 7d 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.

skills/programming/ai-engineering/self-eval/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Eval: Honest Work Evaluation

ultrathink

Tier: STANDARD Category: Engineering / Quality Dependencies: None (prompt-only, no external tools required)

Description

Self-eval is a Claude Code skill that produces honest, calibrated work evaluations. It replaces the default AI tendency to rate everything 4/5 with a structured two-axis scoring system, mandatory devil's advocate reasoning, and cross-session anti-inflation detection.

The core insight: AI self-assessment converges to "everything is a 4" because a single-axis score conflates task difficulty with execution quality. Self-eval separates these axes, then combines them via a fixed matrix that the model cannot override.

Features

  • Two-axis scoring — Independently rates task ambition (Low/Medium/High) and execution quality (Poor/Adequate/Strong), then combines via a lookup matrix
  • Mandatory devil's advocate — Before finalizing, must argue for both higher AND lower scores, then resolve the tension
  • Score persistence — Appends scores to .self-eval-scores.jsonl in the working directory, building history across sessions
  • Anti-inflation detection — Reads past scores and flags clustering (4+ of last 5 identical)
  • Matrix-locked scoring — The composite score comes from the matrix, not from direct selection. Low ambition caps at 2/5 regardless of execution quality

Usage

After completing work in a Claude Code session:

/self-eval

With context about what to evaluate:

/self-eval the authentication refactor we just completed

The skill reviews the conversation history, identifies what was accomplished, scores it on both axes, runs the devil's advocate check, and appends the result to the score history file.

Examples

Example 1: Feature Implementation

/self-eval added pagination to the user list API

Output:

## Self-Evaluation

**Task:** Added cursor-based pagination to the user list API endpoint
**Ambition:** Medium — New feature with established patterns, but required careful backwards compatibility
**Execution:** Strong — All tests pass, handles edge cases, existing clients unaffected

**Devil's Advocate:**
- Lower: Pagination is well-documented. The pattern was copied from another endpoint with minor changes. Could argue Low ambition.
- Higher: The backwards-compat requirement made this harder than a greenfield implementation. Had to support both offset and cursor modes.
- Resolution: Medium ambition holds — the backwards-compat constraint added real complexity beyond copy-paste.

**Score: 4** — Solid execution on meaningful work with real constraints.

Read the full file on GitHub · 186 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. 7d ago First seen · 186 lines · 51 tokens per session scan A 0b829818fd15

Subscribe to this mod's changes

self-eval is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,934 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 2026-08-31.

Related

Other skills, from other repositories

blog-post

Full-stack blog post production — turns a topic, idea, or brief into a complete publishing package across written, social, and multimedia surfaces. Generates broomva.tech .mdx posts (or Substack/other long-form), X posts and threads, LinkedIn posts, Instagram posts and reel scripts, plus multimedia asset plans…

broomva/skills · 182 tokens

content-creation

Full-stack content creation pipeline: idea or reference to published blog post, audio narration, video, and social media distribution. Orchestrates research, reference extraction, storytelling, AI visual assets (Nano Banana, Veo 3.1), TTS audio (Voicebox, kokoro-tts, Edge TTS), Remotion video, and social copy into a…

broomva/skills · 239 tokens

agentic-webdesign-html-anything

Install and use html-anything — the agentic HTML editor where your local AI agent writes HTML and you ship it. 75 skills × 9 surfaces, BYOK, zero API key. Use when building magazine articles, keynote decks, resumes, posters, social cards, web prototypes, data reports, or Hyperframes videos with AI coding agents.

S3YED/appie-kit · 78 tokens

revenuecast

/revenuecast is the verb that turns what you can do into a machine that makes the world want it. You have a real capability — a craft, an expertise, a running system. revenuecast builds the loop where the capability's output becomes its own advertisement, and the demand that output creates is monetized by selling the…

broomva/skills · 389 tokens

citable

Make authored content survive the two selection surfaces it now faces: human engagement and LLM retrieval for citation. These partially anti-correlate, and the tactics that raise reactions are in two measured cases the ones that suppress citation. Encodes effect sizes from published causal studies (Scrunch, 12,000…

broomva/skills · 304 tokens

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens