What is scythe-context-mcp AGENTS.md?

Repository instructions for Scythe Context MCP, a tool that indexes a codebase so an agent can find relevant files, symbols, dependencies, and related code.

Use it when exploring unfamiliar code, preparing focused context for a task, tracing imports and dependencies, or checking whether the repository index is current.

It gives the agent a defined way to search a repository while keeping private files, credentials, and generated indexes out of commits and outputs.

How Lianye-Scythe/scythe-context-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Lianye-Scythe/scythe-context-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.

Copy the file

curl -O https://raw.githubusercontent.com/Lianye-Scythe/scythe-context-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Lianye-Scythe/scythe-context-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lianye-scythe/scythe-context-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/lianye-scythe/scythe-context-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/lianye-scythe/scythe-context-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lianye-scythe/scythe-context-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lianye-scythe/scythe-context-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lianye-scythe/scythe-context-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 356 This file is loaded in full into every session.

When invoked 356 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00356	$0.00356
Opus 5	$0.00178	$0.00178
Sonnet 5	$0.00071	$0.00071
Haiku 4.5	$0.00036	$0.00036

Measured 12d ago against content hash c80ac7239334, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

scythe-context-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 12d 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.

AGENTS.md · 24 lines

What it actually says

Scythe Context MCP Agent Guide

Workflow

Start with repo_index_status to check whether .scythe-context/index.sqlite exists, whether files/chunks/symbols/dependencies/embeddings are present, and whether freshness reports stale files.
If metadata is missing or stale, run repo_reindex with dry_run=false.
Set index_embeddings=true only when semantic search is needed. This sends chunk text to the configured Gemini-compatible endpoint.
Prefer repo_context_pack for task-oriented code lookup. It combines hybrid search, snippet budgeting, related-file metadata, bounded multi-hop traversal, and suggested paths.
Use repo_semantic_search when debugging raw ranking behavior. Prefer a smaller max_context_chars for broad exploration and increase it only when the returned snippets are not enough.
After a search result identifies a useful file, call repo_related_files for that file when you need a focused view of its symbols, imports, and reverse imports.

Privacy

Do not commit .scythe-context/, legacy .repo-beacon/, or local/.
Do not print API keys, proxy tokens, or contents of files under local/secrets/.
Treat third-party Gemini-compatible proxy endpoints as remote services that can see query and chunk text.

Development

Keep indexing, storage, provider, search, and MCP tool wiring decoupled.
Preserve stable chunk row ids for unchanged files so embedding cache remains useful.
Add focused tests when changing scanner, chunker, schema, ranking, formatting, or provider compatibility.
Run npm test, npm run build, and npm audit --omit=dev before committing a completed development slice.

Changes

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.

12d ago First seen · 24 lines · 356 tokens per session scan A c80ac7239334

Subscribe to this mod's changes

scythe-context-mcp AGENTS.md is an instructions file published in the GitHub repository Lianye-Scythe/scythe-context-mcp (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 356 tokens to every session, about $0.0018 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.

Building agents Memory and context code-search codex context-engine gemini-embedding mcp sqlite-vec

repobrain copilot-instructions.md

Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.

study8677/repobrain · 229 tokens

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

scythe-context-mcp: Instructions file for Codex