audit-skill-visibility

A report that checks whether installed Claude Code skills are visible to the model and explains why some may not be selected.

In plain words
What is it for?
Use it to inspect skill-listing budget effects, dropped descriptions, usage-based visibility, and other reasons a skill may be difficult for the model to discover.
Why use it?
A skill that is not included in the model’s visible skill list cannot be chosen, so low use may reflect visibility limits rather than lack of need.

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/melodic-software/claude-code-plugins/audit-skill-visibility
Any agent
npx skills add melodic-software/claude-code-plugins --skill audit-skill-visibility
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code, Codex.

Per session 312 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,976 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 $0.00312 $0.02976
Opus 5 $0.00156 $0.01488
Sonnet 5 $0.00062 $0.00595
Haiku 4.5 $0.00031 $0.00298

Measured today against content hash 27899fa8cc66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-skill-visibility 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 today.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/audit_skill_visibility.py, scripts/audit_skill_visibility.test.sh, scripts/skill-pair-cooccurrence.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/claude-ops/skills/audit-skill-visibility/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Answers one question: can the model actually see each of my skills, and if not, why?

That is the question behind the one operators usually ask, which is why does most of my skill fleet never get used? A skill the model cannot see cannot be chosen, so "unused" is very often a visibility failure wearing a preference costume.

Visibility is Claude Code's own term for this: skillOverrides is documented under "Override skill visibility". This skill audits every way a skill loses it.

Claude Code budgets the model-visible skill listing at a fraction of the context window (skillListingBudgetFraction, default 0.01) and, when it overflows, sheds descriptions from the lowest-scoring skills first. Names always survive, descriptions do not. A skill at zero usage scores zero, so it loses its description, loses the keywords a request would match against, and stays at zero. Unused is partly self-causing.

The budget fraction and per-entry cap are owned by https://code.claude.com/docs/en/settings (skillListingBudgetFraction, skillListingMaxDescChars); that page is authoritative and matches. The drop ORDER is not. https://code.claude.com/docs/en/skills ("Skill descriptions are cut short") says "starting with the skills you invoke least", still as of 2026-08-31; the binary ranks by a decay-weighted score and then walks the list first-fit, so neither the ordering nor the guarantee holds. Take the ordering from the binary: reference/listing-scorer.md carries the counterexamples, the greps, and the stamp.

So the useful question is not which skills are unused. Claude Code already reports that in /doctor and the Stats tab. It is which skills are starved by that loop and still wanted, versus genuinely unwanted, versus not observable at all.

The refusal that defines this skill

A usage store younger than the window being asked about cannot distinguish "never invoked" from "never observed". Reporting the second as the first libels most of a fleet on any fresh install. Measured here: a 3-day-old install against 30/90-day tiers put 210 of 213 skills in a "never used" bucket.

Read the full file on GitHub · 218 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. today Changed · +18 lines · -1 tokens per session 27899fa8cc66
  2. 2d ago First seen · 200 lines · 313 tokens per session scan A 72312703530e

Subscribe to this mod's changes

audit-skill-visibility is a skill published in the GitHub repository melodic-software/claude-code-plugins (13 stars, last pushed today), licensed MIT. It adds 312 tokens to every session and 2,976 once invoked, about $0.0016 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

cli-usage

Complete reference for the systemprompt CLI - 8 domains, 64+ subcommands for managing AI infrastructure, services, agents, cloud deployments, and analytics.

systempromptio/systemprompt-marketplace · 35 tokens

mcp-building

Build MCP servers for systemprompt.io with tools, artifacts, UI resources, and AI service integration.

systempromptio/systemprompt-marketplace · 23 tokens

cli-extension-building

Build standalone CLI extension binaries for systemprompt.io with clap, manifest discovery, and subprocess integration.

systempromptio/systemprompt-marketplace · 22 tokens

systemprompt-tools

Call the free systemprompt.io tools API from any agent: EU AI Act risk classification, CLAUDE.md scoring, llms.txt/AGENTS.md generation and validation, GitHub Actions permissions, and AI ROI calculation. No API key, no signup.

systempromptio/systemprompt-marketplace · 56 tokens

skill-guide

Design, write, and review SKILL.md files using proven patterns. Use when creating, improving, or reviewing agent skills, choosing a design pattern (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline), structuring progressive disclosure, writing skill descriptions, or composing patterns. Also trigger for 'skill…

AndyElessar/skills · 102 tokens

plugin-creator

Guide AI agents through creating GitHub Copilot CLI and Claude Code plugins and plugin marketplaces — from scaffolding plugin directories and writing plugin.json manifests to building marketplace.json registries and testing installations. Use this skill whenever the user wants to create, scaffold, configure, package…

AndyElessar/skills · 181 tokens