ctxharness: Skill for Claude Code

.claude/skills/eval-skills/SKILL.md

eval-skills is a skill for Claude Code from FlorianBruniaux/ctxharness. It costs 66 tokens per session (919 once invoked), scanned A, original, MIT.

A quality checker for reusable agent instruction sets stored in .claude/skills/. It checks their metadata, permitted tools, structure, and written guidance, then scores each one and recommends an effort level.

In plain words
What is it for?
Use it when reviewing skills before shipping, onboarding skills from another project, or adding effort settings to existing skills.
Why use it?
It helps identify skills that are incomplete, too broadly permitted, poorly structured, or mismatched with the amount of work they require.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

This is FlorianBruniaux/ctxharness's own configuration. It tells Claude Code how to work on ctxharness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ctxharness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FlorianBruniaux/ctxharness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FlorianBruniaux/ctxharness/main/.claude/skills/eval-skills/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/ctxharness

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 eval-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/florianbruniaux/ctxharness/eval-skills/github.svg)](https://agentmods.dev/skills/florianbruniaux/ctxharness/eval-skills)
Your own site
<a href="https://agentmods.dev/skills/florianbruniaux/ctxharness/eval-skills"><img src="https://agentmods.dev/badge/skills/florianbruniaux/ctxharness/eval-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eval-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/florianbruniaux/ctxharness/eval-skills"><img src="https://agentmods.dev/badge/skills/florianbruniaux/ctxharness/eval-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 54
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 55
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Agent Snooping · line 2
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 14
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 54
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 55
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00066 $0.00919
Opus 5 $0.00033 $0.00460
Sonnet 5 $0.00013 $0.00184
Haiku 4.5 $0.00007 $0.00092

Measured 10d ago against content hash 03e613e93801, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eval-skills scanned grade A with 1 finding 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 10d 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.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

find .claude/skills -name "SKILL.md" 2>/dev/null

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/eval-skills/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Evaluator

Discover all skills, score them across 6 criteria, and infer the appropriate effort level based on content analysis.

When to Use

  • After adding new skills to ctxharness .claude/skills/
  • Before cutting a release (quality gate)
  • After bulk-importing skills from another project
  • When adding effort fields for the first time

Scoring Criteria (14 pts per skill)

# Criterion Max What is checked
1 name 1 Present, lowercase, hyphens only, matches directory name
2 description 2 Present + has "Use when" / trigger phrasing
3 allowed-tools 2 Present + not overly broad (Bash without scoping when read-only)
4 effort 3 Present (1pt) + appropriate for content (2pt based on inference)
5 content structure 4 Has Purpose/When section (1), has examples/usage (1), has clear workflow (1), no placeholder text (1)
6 bonus +2 argument-hint present (1), version/author metadata (1)

Thresholds:

  • ✅ Good: ≥11/14 (≥80%)
  • ⚠️ Needs work: 8–10/14 (60–79%)
  • ❌ Fix: <8/14 (<60%)

Effort Level Inference

low — Mechanical execution, no design decisions

Signals: commit, scaffold, generate, format, sync. No sub-agents. Short workflow (<5 steps).

medium — Analysis with bounded scope

Signals: review, triage, analyze, evaluate (single file or bounded scope). May spawn 1-2 sub-agents with predefined scope.

high — Design decisions, adversarial reasoning, cross-system analysis

Signals: architect, threat-model, audit (security), orchestrate (multi-agent). Broad tool access. Spawns multiple sub-agents.

If a skill has effort: already set but the inferred level differs, flag it:

⚠️ Effort mismatch: declared low, inferred high

Execution Instructions

Step 1 — Discovery

find .claude/skills -name "SKILL.md" 2>/dev/null
find .claude/skills -maxdepth 1 -name "*.md" ! -name "README*" 2>/dev/null

Read the full file on GitHub · 99 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. 10d ago First seen · 99 lines · 66 tokens per session scan A 03e613e93801

Subscribe to this mod's changes

eval-skills is a skill published in the GitHub repository FlorianBruniaux/ctxharness (21 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 919 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.