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/magnusnoeddegaard/tskills/claude-mdgit clone --depth 1 https://github.com/magnusnoeddegaard/tskillsWrote 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/magnusnoeddegaard/tskills/claude-md)<a href="https://agentmods.dev/instructions/magnusnoeddegaard/tskills/claude-md"><img src="https://agentmods.dev/badge/instructions/magnusnoeddegaard/tskills/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 5.1 | $0.01127 | $0.01127 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
tskills 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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tskills
A package manager for AI skills. Publish, discover, and install skills across Claude Code, Cursor, Copilot, and Windsurf. Backed by a Supabase registry with GitHub OAuth, organizations, teams, and semantic versioning.
Project Structure
src/
├── cli.ts # Entry point, registers all commands
├── types.ts # TypeScript interfaces (Skill, Registry, Org, Team types)
├── commands/ # CLI commands
│ ├── setup.ts # One-command GitHub repo setup (legacy)
│ ├── init.ts # Initialize skills directory (legacy)
│ ├── add.ts # Create new skill from template
│ ├── import.ts # Import existing SKILL.md files
│ ├── list.ts # List discovered skills
│ ├── sync.ts # Pull from remote and sync to tools
│ ├── share.ts # Generate share command + invite collaborators (legacy)
│ ├── config.ts # View/edit configuration
│ ├── login.ts # GitHub OAuth login (opens browser, local callback server)
│ ├── logout.ts # Sign out and clear credentials
│ ├── whoami.ts # Display current user
│ ├── publish.ts # Publish skill to registry (versioning, visibility, org/team)
│ ├── install.ts # Install skill from registry and sync to tools
│ ├── uninstall.ts # Remove installed skill from tools and cache
│ ├── search.ts # Search registry (query, tags, tools filters)
│ ├── info.ts # Show detailed skill info and version history
│ ├── outdated.ts # Check installed skills for available updates
│ ├── update.ts # Update installed skills to latest version
│ ├── deprecate.ts # Mark/unmark skill as deprecated
│ ├── org.ts # Organization management (create, list, info, add, remove, delete)
│ └── team.ts # Team management (create, list, info, add, remove, delete)
├── adapters/ # Tool-specific output adapters
│ ├── types.ts # ToolAdapter interface
│ ├── claude.ts # Claude Code + Copilot (shared location)
│ ├── cursor.ts # Cursor (.mdc format)
│ └── windsurf.ts # Windsurf (.windsurfrules)
└── lib/ # Core utilities
├── config.ts # Read/write ~/.tskills/config.toml
├── discover.ts # Auto-discover SKILL.md files
├── git.ts # Clone/pull operations (uses gh CLI)
├── skill.ts # Parse SKILL.md with YAML frontmatter
├── credentials.ts # Save/load/clear auth tokens (~/.tskills/credentials.json)
├── errors.ts # Custom error classes (Auth, Network, Validation, RateLimit, etc.)
├── error-handler.ts # Map Supabase/Postgres/FS errors to custom errors
├── manifest.ts # Track installed skills (~/.tskills/installed.json)
├── registry.ts # Supabase client + full registry API (skills, orgs, teams, rate limits)
├── registry-config.ts # Dynamic registry config with remote fetch + caching
├── retry.ts # Retry with exponential backoff and jitter
└── validation.ts # Input validation (skill names, semver, org/team slugs, etc.)
supabase/
├── config.toml # Supabase project configuration
└── migrations/ # 14 SQL migrations (schema, RLS, functions, fixes)
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.
- 6d ago First seen · 103 lines · 1,127 tokens per session scan A da10f195a542
tskills CLAUDE.md is an instructions file published in the GitHub repository magnusnoeddegaard/tskills (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,127 tokens to every session, about $0.0056 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
mcp-unity AGENTS.md
AGENTS.md instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
rails-ai-context AGENTS.md
AGENTS.md instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
inspecto CLAUDE.md
Claude Code instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.