skillr CLAUDE.md

skillr CLAUDE.md is an instructions file for coding agents from eooo-io/skillr. It costs 794 tokens per session, scanned A, original, MIT.

Repository instructions for Skillr, a command-line tool that turns shared AI instructions into configuration files for several coding assistants.

In plain words
What is it for?
Use them when working on Skillr’s CLI, its instruction formats, provider integrations, commands, or synchronization features.
Why use it?
They help an agent understand the repository’s purpose, layout, technology, and development workflow before changing code.

Instructions file

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 instructions/eooo-io/skillr/claude-md
Clone the repo
git clone --depth 1 https://github.com/eooo-io/skillr

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 skillr CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eooo-io/skillr/claude-md.svg)](https://agentmods.dev/instructions/eooo-io/skillr/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eooo-io/skillr/claude-md"><img src="https://agentmods.dev/badge/instructions/eooo-io/skillr/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 794 This file is loaded in full into every session.
When invoked 794 The same file — it is already loaded in full.
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 $0.00794 $0.00794
Opus 5 $0.00397 $0.00397
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00079 $0.00079

Measured 3d ago against content hash 357c1cd43fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillr CLAUDE.md 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 3d 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.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file orients Claude Code (and other agentic tools) when working in this repo.

Project direction

Skillr is a portable AI instruction format with cross-provider sync. You define skills once under .skillr/ and compile them to 11 native provider configs (Claude, Cursor, Copilot, Windsurf, Cline, OpenAI Codex, Zed, Aider, Continue, Junie, plus legacy OpenAI). The legacy openai driver is deprecated in favor of codex (which writes AGENTS.md) and will be removed in v1.2.0.

The primary artifact is the CLI, published to npm as @eooo/skillr. The Laravel web app under app/ and React UI under ui/ are legacy from an earlier phase and are not the current focus.

Repo layout

cli/                      # The published package — TypeScript + Commander
  src/
    cli.ts                # Command entry point
    commands/             # init, add, remove, list, sync, diff, lint, import, test, providerAdd
    services/             # Manifest, SkillFileParser, SkillCompositionService,
                          # TemplateResolver, PromptLinter, SyncService,
                          # ConditionEvaluator
    drivers/              # Built-in provider drivers + registry (getDriver,
                          # registerDriver, loadPlugins)
    types.ts              # Spec v1 types (SkillFrontmatter, ResolvedSkill,
                          # ProviderPlugin, etc.)
  package.json            # Published as @eooo/skillr
docs/                     # VitePress user-facing docs
app/, ui/, database/      # Legacy Laravel/React dashboard (not active)
.github/workflows/        # CI (tests + build) and npm-publish (on v* tag)
PLAN.md                   # SemVer roadmap and milestone status

Tech stack (CLI)

Layer Tool
Language TypeScript 5.8, targeting ES2022
CLI framework Commander 13
Parser js-yaml (frontmatter), fast-glob (file discovery)
Tests Vitest (145+ tests)
Build tsc → dist/

Dev workflow

cd cli
npm install
npm run dev -- <subcommand>   # Runs src/cli.ts via tsx
npm run build                  # Emits dist/
npm test -- --run              # One-shot vitest run (CI mode)

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 794 tokens per session scan A 357c1cd43fc9

Subscribe to this mod's changes

skillr CLAUDE.md is an instructions file published in the GitHub repository eooo-io/skillr (2 stars, last pushed 1mo ago), licensed MIT. It adds 794 tokens to every session, about $0.0040 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.