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/deevus/tea-skills/claude-mdgit clone --depth 1 https://github.com/deevus/tea-skillsWrote 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/deevus/tea-skills/claude-md)<a href="https://agentmods.dev/instructions/deevus/tea-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/deevus/tea-skills/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 | $0.00989 | $0.00989 |
| Opus 5 | $0.00495 | $0.00495 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
tea-skills 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Claude Code plugin providing skills for Gitea/Forgejo workflows via the tea CLI. Installed with claude mcp add-plugin tea /path/to/tea-skills. There is no build system or package manager — this is markdown plus Python bundled actions.
Architecture
Focused Single-File Skills
Each skill lives in its own directory with a single skills/<name>/SKILL.md file. Skills are action-specific (e.g., create-issue, merge-pull) rather than domain-broad, keeping each skill focused and readable.
Issues domain: list-issues, create-issue, edit-issues, close-issues, issue-comments, issue-dependencies, issue-moderation
Pulls domain: list-pulls, create-pull, review-pull, merge-pull, close-pulls
Milestones domain: milestones, milestone-issues
Labels domain: labels, label-schemes
Skill Routing
Skills are user-invokable directly from skills/<name>/SKILL.md. There is currently no commands/ directory; keep any future command stubs thin and route behavior back to the corresponding skill.
Actions for API Gaps
actions/ contains bundled Python actions for Gitea/Forgejo features the tea CLI lacks. Skill docs refer to them as actions/<domain>/<action> following the bundled-resource convention: resolve that path relative to this installed plugin, then execute the absolute action path while keeping the working directory in the target repository. Do not require users to cd into the plugin root or put actions/ on PATH.
Actions are action-specific and organized by domain folders. Domain README files document normal tea CLI commands first and bundled actions second. Prefer tea wherever it supports the workflow.
Private HTTP support lives in actions/internal/tea_api.py. It is stdlib-only Python and is not a user-facing Interface.
Plugin Registration
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 · 68 lines · 989 tokens per session scan A 266495e5bc22
tea-skills CLAUDE.md is an instructions file published in the GitHub repository deevus/tea-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 989 tokens to every session, about $0.0049 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
gitea-mcp-server AGENTS.md
AGENTS.md instructions for pxsloot/gitea-mcp-server, covering agent guidelines, what we build, developer handbook and fastmcp documentation.
forgejo-mcp CLAUDE.md
Instructions for raohwork/forgejo-mcp, covering forgejo mcp server, project overview, supported operations, transport modes and architecture.
gitops-landing-zone CLAUDE.md
Claude Code instructions for bogdandragosvasile/gitops-landing-zone, covering gitops landing zone — agent federation, what is this, architecture, agent protocol and execution phases.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.