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/gitopia/gitopia-mcp-server/claude-mdgit clone --depth 1 https://github.com/gitopia/gitopia-mcp-serverWhat 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 | $0.00921 | $0.00921 |
| Opus 5 | $0.00461 | $0.00461 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
gitopia-mcp-server 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 yesterday.
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.
Gitopia MCP Server
Decentralized Git + blockchain bounties + DAO governance via the Model Context Protocol.
57 tools, 3 prompts, 4 resource templates.
Architecture
3-layer design: MCP client -> handler (internal/handler/) -> registration (cmd/server/main.go).
Key packages:
cmd/server/— entry point, server initializationinternal/handler/register.go— tool/prompt/resource registrationinternal/handler/— tool handler implementations (params structs + handler methods onToolHandler). Includes tag_handlers.go, commit_handlers.go, release_handlers.go, label_handlers.go for tags/commits/releases/labelsinternal/gitopia/— gRPC client for Gitopia chain queries and tx signinginternal/signing/— wallet management, transaction signing, fee grantsinternal/config/— configuration loading (file + env var overlay)internal/git/— local git operationsinternal/workspace/— sandboxed workspace path resolution
Build & Test
go build ./cmd/server # compile server binary
go test ./... # run all tests
go vet ./... # static analysis
go test -cover ./internal/handler/... # handler coverage
Environment Variables
| Variable | Purpose | Default |
|---|---|---|
GITOPIA_MNEMONIC |
BIP-39 mnemonic for signing | auto-generated if not set |
GITOPIA_GRPC_ENDPOINTS |
Comma-separated gRPC endpoints | gitopia-grpc.polkachu.com:11390 |
DRY_RUN |
true/1 to preview without broadcasting |
false |
TRUST_LEVEL |
readonly, localwrite, chainwrite |
chainwrite |
TOOLSETS |
Comma-separated toolsets (core, workflow, or all) |
all |
TRANSPORT |
stdio or http |
stdio |
PORT |
HTTP listen port (when TRANSPORT=http) | 8080 |
GITOPIA_WALLET_BACKEND |
mnemonic, keyring, file, or auto |
auto |
APPROVAL_MODE |
true/1 to require confirmation before chain-write broadcast |
false |
APPROVAL_TTL |
Duration before pending transactions expire | 5m |
MCP_CONFIG_FILE |
Path to JSON config file | ~/.mcp/gitopia/config.json |
MCP_LOG_LEVEL |
Log level (debug, info, warn, error) | info |
MCP_WORKSPACE_PATH |
Workspace root for cloned repos | ~/.mcp/gitopia/workspace |
GIT_USER_NAME |
Default git user name | Gitopia MCP Server |
GIT_USER_EMAIL |
Default git user email | [email protected] |
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.
- yesterday First seen · 73 lines · 921 tokens per session scan A f8d6137ea1a1
gitopia-mcp-server CLAUDE.md is an instructions file published in the GitHub repository gitopia/gitopia-mcp-server (3 stars, last pushed 5mo ago), licensed MIT. It adds 921 tokens to every session, about $0.0046 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.