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.
npx agentmods add instructions/eooo-io/skillr/claude-mdgit clone --depth 1 https://github.com/eooo-io/skillrWrote 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.
[](https://agentmods.dev/instructions/eooo-io/skillr/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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)
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.
- 3d ago First seen · 68 lines · 794 tokens per session scan A 357c1cd43fc9
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.
Other instructions, from other repositories
assaio AGENTS.md
Instructions for assaio/assaio, covering agents.md — assaio, what this is, code philosophy (non-negotiable), code standards (enforced + human-reviewed) and honesty rules (product-critical).
Overture CLAUDE.md
Instructions for SixHq/Overture, covering claude.md, project overview, monorepo structure, build & development commands and install dependencies (from root).
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge copilot-instructions.md
Copilot instructions for srnichols/plan-forge, covering instructions for copilot, architecture principles, core principles (non-negotiable), cost estimates and talking to forge-master.
plan-forge testing.instructions.md
Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.
plan-forge landing-zone.instructions.md
Azure Landing Zone baselines — identity, network, policy, management, security, tagging, subscription organization.