agentmods.dev

scythe-context-mcp: Instructions file for Codex

AGENTS.md

scythe-context-mcp AGENTS.md is an instructions file for Codex, OpenCode from Lianye-Scythe/scythe-context-mcp. It costs 356 tokens per session, scanned A, original, Apache-2.0.

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

In plain words
What is it for?
Use it when exploring unfamiliar code, preparing focused context for a task, tracing imports and dependencies, or checking whether the repository index is current.
Why use it?
It gives the agent a defined way to search a repository while keeping private files, credentials, and generated indexes out of commits and outputs.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Lianye-Scythe/scythe-context-mcp's own configuration. It tells Codex and OpenCode how to work on scythe-context-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scythe-context-mcp configures →

not rated 1repo 19d ago A scan 356 tokens original Apache-2.0 archived
View source ↗ Lianye-Scythe/scythe-context-mcp npmjs.com
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.

agentmods badge for scythe-context-mcp AGENTS.md

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.

agentmods 80×15 button for scythe-context-mcp AGENTS.md

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00356 $0.00356
Opus 5.5 $0.00142 $0.00142
Sonnet 5.5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured 2mo ago against content hash c80ac7239334, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

  1. 2mo 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 (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 356 tokens to every session, about $0.0014 per session on Opus 5.5. 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 agentsMemory and contextcode-searchcodexcodex-clicontext-enginemcpmcp-server
Related

scythe-context-mcp AGENTS.md compared with instructions from other repositories

scythe-context-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
scythe-context-mcp AGENTS.mdLianye-Scythe/scythe-context-mcpInstructions file119d agoApache-2.0A356Codex, OpenCode
repobrain copilot-instructions.mdstudy8677/repobrainInstructions file1.4k14d agoMITA229GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot