Borrowing it
Nothing to install: this file belongs to v-o-h-s/osc-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/v-o-h-s/osc-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/v-o-h-s/osc-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/v-o-h-s/osc-mcp/agents-md)<a href="https://agentmods.dev/instructions/v-o-h-s/osc-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/v-o-h-s/osc-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 5.1 | $0.01388 | $0.01388 |
| Opus 5 | $0.00694 | $0.00694 |
| Sonnet 5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
osc-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 7d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — osc-mcp
Agent instructions for the osc-mcp codebase. Read this before writing any code.
Project Overview
An MCP (Model Context Protocol) server that bridges AI coding agents with the OpenCode SQLite database.
- opencodeDb — OpenCode's DB (
~/.local/share/opencode/opencode.db). Read-only in practice. - mcpDb — Our DB (
~/.local/share/opencode/osc-mcp/mcp.db). We own schema and writes.
Commands (Bun only)
# Install dependencies
bun install
# Run all tests
bun test
# Run a single test file
bun test tests/storePreviousSessionContent.test.ts
# Run a specific test by name pattern
bun test --test-name-pattern "returns no previous session"
# Type-check (no emit)
bunx tsc --noEmit
# Run the MCP server
bun src/index.ts
- No dedicated lint/format command in this repo.
- Never use
node,ts-node,npx,jest, orvitest. Always usebun/bunx.
Tool Catalog (src/index.ts)
Registered MCP tools:
-
store_previous_session_content— stores filtered content for the most recent previous session. -
get_relevant_sessions— returns 10 most recent sessions (title, date, id) for a TOC. -
Input validation uses Zod schemas and
zodToJsonSchemafor tool manifests. -
CallToolRequestSchemaparses args withSchema.parse(args || {}). -
Errors are returned as
{ content: [{ type: "text", text:Error: ...}], isError: true }.
Database Details (src/db.ts)
- Paths resolve to
~/.local/share/opencode/{opencode,osc-mcp/mcp}.dbunless overridden byOPENCODE_DB/MCP_DB. - PRAGMAs:
busy_timeout=5000on both DBs,journal_mode=WALonmcpDb. - Schema created on startup:
mcp_session_summary(session_id TEXT PRIMARY KEY, project_id TEXT, content TEXT, time_created INTEGER, time_updated INTEGER).
Adding a New Tool
Every tool file must export:
- A Zod schema named
<ToolName>InputSchema - A
typeinferred from the schema - An
async functionimplementing the tool
Then register it in src/index.ts:
- Add to the
ListToolsRequestSchemahandler'stoolsarray - Add a
casein theCallToolRequestSchemaswitch
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.
- 7d ago First seen · 151 lines · 1,388 tokens per session scan A a42f9daa37fc
osc-mcp AGENTS.md is an instructions file published in the GitHub repository v-o-h-s/osc-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,388 tokens to every session, about $0.0069 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
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.
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.
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).
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).
langchain AGENTS.md
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.
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.