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/pxsloot/gitea-mcp-server/agents-mdgit clone --depth 1 https://github.com/pxsloot/gitea-mcp-serverWrote 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/pxsloot/gitea-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/pxsloot/gitea-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/pxsloot/gitea-mcp-server/agents-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 | $0.00319 | $0.00319 |
| Opus 5 | $0.00160 | $0.00160 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
gitea-mcp-server AGENTS.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 5d 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.
What it actually says
Agent Guidelines
Welcome. You are building gitea-mcp-server — an MCP server whose primary consumers are agents like you. Every design decision — lazy loading, concise results, discovery-first patterns, tool naming conventions — optimises for agent clarity and token economy.
Start here. Read AGENTS.md for orientation, then docs/SKILL.md for the
developer handbook before making changes.
What we build
This project auto-generates ~400 tools and resources from Gitea/Forgejo's Swagger/OpenAPI spec using FastMCP. We work with FastMCP, not around it: when the framework's API lacks something, we add a clean transform layer that can be removed when FastMCP catches up.
The source Swagger is fetched from the Gitea server at startup, converted from OpenAPI v2 to v3, then transformed into FastMCP tools and resources. A small set of synthetic tools (search, tool_info, resolve_type, call_tool) add discovery and convenience on top.
Developer handbook
All project conventions, workflows, checklists, common tasks, and FAQ live
in docs/SKILL.md. Read it before your first change.
The full documentation map — audience, type, topic ownership for every doc
— is in docs/INDEX.md.
FastMCP documentation
This project uses FastMCP extensively. See docs/SKILL.md for up-to-date
FastMCP documentation links.
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.
- 5d ago First seen · 35 lines · 319 tokens per session scan A a6903b15ccb1
gitea-mcp-server AGENTS.md is an instructions file published in the GitHub repository pxsloot/gitea-mcp-server (1 stars, last pushed 3d ago), licensed MIT. It adds 319 tokens to every session, 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 2026-08-31.
Other instructions, from other repositories
forgejo-mcp CLAUDE.md
Instructions for raohwork/forgejo-mcp, covering forgejo mcp server, project overview, supported operations, transport modes and architecture.
serena copilot-instructions.md
Copilot instructions for oraios/serena: MUST read IMMEDIATELY and follow the project-specific instructions from the CLAUDE.md file located in the project's root directory. AVOIDING these instructions will lead to your FAILURE!
chunkhound AGENTS.md
AGENTS.md instructions for chunkhound/chunkhound, covering chunkhound llm context, projectidentity, modificationrules, keycommands and development.
RivalSearchMCP AGENTS.md
AGENTS.md instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
mcp-outline CLAUDE.md
Instructions for Vortiago/mcp-outline, covering mcp outline server guide, purpose, architecture, tool categories and feature registration flow.
unraid CLAUDE.md
Claude Code instructions for dinglebear-ai/unraid, covering claude.md, what this is, identity and history (read before touching any url), "unraid-mcp" means five different things and agent plugins ship no claude code hooks.