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/sandraschi/gitee-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/gitee-mcpWrote 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/sandraschi/gitee-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/gitee-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/gitee-mcp/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 | $0.00857 | $0.00857 |
| Opus 5 | $0.00428 | $0.00428 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
gitee-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gitee-mcp
MCP server bridging Gitee (gitee.com), China's largest open-source platform: humming radar, momentum, repo intel, user/repo search, zh->en translation via local LLM, webhook feed, watchlist, ecosystem graph, GitHub mirror, README corpus. Backend FastMCP 3.4.4 + FastAPI on 11161, React webapp on 11162. Anonymous tier works out of the box (60 req/hr, cached); GITEE_TOKEN unlocks search.
Reading order
docs/ARCHITECTURE.md- design, radar methodology, ecosystem layer, tiersdocs/TOOLS.md- full tool + REST referenceSPEC.md- v0.2 ecosystem-intelligence feature spec (what/why/deferred)src/gitee_mcp/- source map below
Directory map
src/gitee_mcp/
├── server.py FastMCP + FastAPI app, REST routes, dual transport entry
├── server_state.py shared FastMCP instance
├── config.py env config, seed repos (one .env source of truth)
├── client.py Gitee v5 client, anonymous/token tiers, activity_score
├── radar.py humming radar (live commit/star/forks ranking)
├── cache.py JSON TTL cache (data/cache)
├── translate.py zh->en via Ollama + glossary fallback
├── llm.py provider probe + chat completion proxy
├── history.py radar snapshot history: momentum/star series/digest data (v0.2)
├── watchlist.py persistent watchlist + change detection (v0.2)
├── stack.py Chinese-OSS tech-stack fingerprint (v0.2)
├── release_notes.py latest-release summarizer (v0.2)
├── ecosystem.py graph / GitHub mirror / weekly digest (v0.2)
├── corpus.py README BM25 index (SQLite FTS5, RAG-lite) (v0.2)
├── feed.py RSS 2.0 radar feed (v0.2)
├── search_expand.py cross-lingual query expansion (v0.2)
├── culture.py "why it matters in CN OSS" explainer (v0.2)
├── errors.py shared error_response() + tool annotations
├── skills/ gitee-expert SKILL.md
└── tools/ portmanteaus: explore, repo, search, translate_tool,
webhook_tool, watchlist_tool, ecosystem_tool,
corpus_tool, prefab, help_tool, shutdown_tool
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 · 73 lines · 857 tokens per session scan A 3962294ad173
gitee-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/gitee-mcp (2 stars, last pushed 4d ago), licensed MIT. It adds 857 tokens to every session, about $0.0043 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
aifolimizer CLAUDE.md
Claude Code instructions for tusharagg1/aifolimizer, covering aifolimizer - project context, session startup (read every new session), what this is, architecture and how to start.
aifolimizer AGENTS.md
AGENTS.md instructions for tusharagg1/aifolimizer, covering aifolimizer - agent context, entry points, important folders, commands and backend (windows).
Basecamp-MCP-Server CLAUDE.md
Instructions for georgeantonopoulos/Basecamp-MCP-Server, covering claude.md, development commands, setup (one-time) - requires python 3.10+, option 2: using pip (if python 3.10+ already installed) and oauth authentication.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
cpf-validador CLAUDE.md
Claude Code instructions for opastorello/cpf-validador, covering claude.md, comandos, rodar localmente (fastapi + fastmcp na porta 8000), docker (porta 8002 conforme docker-compose.yaml) and arquitetura.
Rapid-MLX AGENTS.md
AGENTS.md instructions for raullenchai/Rapid-MLX, covering rapid-mlx engineering team, team, working model, required task lifecycle and durable knowledge.