evaluate

evaluate is a skill for Claude Code, Codex from mishahanin/heading-os. It costs 99 tokens per session (1,733 once invoked), scanned A, original, Apache-2.0.

A quality-review service for workspace files such as skills, scripts, reference documents, and rules. It runs automated checks and then assesses clarity, quality, and completeness.

In plain words
What is it for?
Use it after implementation or revision to evaluate a file or directory against workspace standards and a plan’s success criteria.
Why use it?
It provides both mechanical test results and a skeptical human-like review before an artifact is considered ready.

Skill for Claude CodeCodex

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/mishahanin/heading-os/evaluate
Any agent
npx skills add mishahanin/heading-os --skill evaluate
Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os

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 evaluate

README.md
[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/evaluate.svg)](https://agentmods.dev/skills/mishahanin/heading-os/evaluate)
Your own site
<a href="https://agentmods.dev/skills/mishahanin/heading-os/evaluate"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/evaluate.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,733 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 $0.00099 $0.01733
Opus 5 $0.00049 $0.00866
Sonnet 5 $0.00020 $0.00347
Haiku 4.5 $0.00010 $0.00173

Measured 5d ago against content hash 72bf3e5d0508, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate 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 5d 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.

.claude/skills/evaluate/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate

Skeptical quality evaluator for workspace artifacts. Runs a two-layer assessment: deterministic checks (automated script) followed by qualitative judgment (you, the skeptical reviewer).

Variables

artifact_path: $ARGUMENTS (path to artifact - skill directory, script file, reference file, or rule)

Parse arguments: extract artifact_path and optional --plan <plan-path> from $ARGUMENTS.


Instructions

Phase 0: Context Loading

  1. Determine what to evaluate. Parse artifact_path from arguments.
  2. Detect artifact type from path:
    • .claude/skills/*/SKILL.md or skill directory -> skill
    • scripts/*.py -> script
    • reference/*.md -> reference
    • .claude/rules/*.md -> rule
  3. Read the artifact completely. Do not skim.
  4. If --plan provided, read the plan's Success Criteria and Validation Checklist sections.
  5. Load the evaluator rubric: read .claude/skills/evaluate/references/evaluator-rubric.md

Phase 1: Deterministic Evaluation

Run the automated evaluation script:

python3 scripts/artifact-evaluator.py --path <artifact_path> --json [--plan <plan-path>]

Parse the JSON output. Record all pass/fail/warn results. These are objective, non-negotiable checks - if the script says FAIL, it's a FAIL.


Phase 2: Qualitative Evaluation

Your persona for this phase:

You are a skeptical reviewer. Your job is to find problems, not confirm quality. Assume the generator took shortcuts. Look for evidence of thoroughness. Grade on the artifact as delivered, not on effort or intent. The burden of proof to pass is on the artifact.

Do NOT be generous. Do NOT give benefit of the doubt. A mediocre artifact that checks the boxes is worse than a rejected artifact that gets fixed.

Evaluate based on artifact type:

For Skills
  1. Instruction clarity - Could someone execute every phase unambiguously? Are there steps that say "do something appropriate" without specifying what? Flag any vagueness.
  2. Trigger accuracy - Does the description clearly convey WHEN to trigger and WHEN NOT to? Would this skill fire on prompts meant for other skills?
  3. Edge case coverage - What happens with missing arguments? Empty input? Unusual paths? Does the skill handle failure gracefully?
  4. Voice consistency - Does it follow workspace conventions (hyphens not dashes, ODUN.ONE, DPI+, maritime vocabulary where appropriate)?
  5. Phase completeness - Does each phase produce a defined output that feeds the next? Or are there gaps?

Read the full file on GitHub · 187 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 187 lines · 99 tokens per session scan A 72bf3e5d0508

Subscribe to this mod's changes

evaluate is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 1,733 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 69 tokens

merge-strategy

Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…

marcus/sidecar · 63 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

agent-communication-protocol

Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.

majiayu000/claude-skill-registry · 25 tokens

openlore-brainstorm

Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.

clay-good/OpenLore · 40 tokens