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/muvon/octocode/agents-mdgit clone --depth 1 https://github.com/Muvon/octocodeWrote 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/muvon/octocode/agents-md)<a href="https://agentmods.dev/instructions/muvon/octocode/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octocode/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 | $0.02451 | $0.02451 |
| Opus 5 | $0.01226 | $0.01226 |
| Sonnet 5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
octocode 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 4d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octocode — AI-Powered Code Intelligence
Rust CLI tool (v0.14.x) that indexes codebases into LanceDB vector stores, builds knowledge graphs via GraphRAG, and exposes everything through an MCP server for AI assistant integration. Core stack: Rust + tokio + LanceDB + tree-sitter + octolib (embedding/LLM providers). Embedding providers and LLM are delegated entirely to octolib.
Project Structure
src/
main.rs — CLI entry point, command dispatch
config.rs — All config structs; NO runtime defaults (panic on missing)
storage.rs — Project DB path resolution (~/.local/share/octocode/<hash>/)
store/ — LanceDB operations
mod.rs — Store struct, block types (CodeBlock, TextBlock, DocumentBlock, CommitBlock)
vector_optimizer.rs — Auto-tuned IVF_RQ / IVF_HNSW_SQ index selection
batch_converter.rs — Arrow RecordBatch construction
table_ops.rs — content_exists(), low-level table ops
graphrag.rs — GraphRAG node storage
metadata.rs — Table metadata helpers
embedding/mod.rs — Thin wrapper over octolib; generate_embeddings*, hash utilities
llm/mod.rs — Thin wrapper over octolib LLM; LlmClient::from_config()
indexer/
mod.rs — NoindexWalker, file pipeline orchestration
languages/ — One file per language, all implement Language trait
graphrag/ — GraphRAG builder, AI relationship discovery
batch_processor.rs — Batch embedding + flush logic
differential_processor.rs — Incremental file change processing
contextual.rs — LLM-based contextual chunk enrichment
commits/ — Git commit history indexing
mcp/
server.rs — McpServer (rmcp-based, stdin + HTTP modes)
semantic_code.rs — SemanticCodeProvider tool impl
graphrag.rs — GraphRagProvider tool impl
lsp/ — LSP integration tools
proxy.rs — Multi-repo MCP proxy
commands/ — One file per CLI subcommand
config-templates/default.toml — Single source of truth for ALL config defaults
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.
- 4d ago First seen · 189 lines · 2,451 tokens per session scan A ed126aa6a6da
octocode AGENTS.md is an instructions file published in the GitHub repository Muvon/octocode (465 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,451 tokens to every session, about $0.0123 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 2026-08-30.
Other instructions, from other repositories
codesearch AGENTS.md
Instructions for flupkede/codesearch, covering agents.md — codesearch, current state, implemented features, open todos and ⚠️ branching & pr workflow (read first).
mimirs CLAUDE.md
Claude Code instructions for TheWinci/mimirs, a project described as: Local MCP server that gives AI coding agents persistent, searchable memory of your codebase.
hound-mcp CLAUDE.md
Claude Code instructions for jmagly/hound-mcp, covering provider workspace bootstrap and provider workspace bootstrap.
ContextFlux AGENTS.md
AGENTS.md instructions for divyanshu-iitian/ContextFlux, a project described as: Task-adaptive repository context engine for coding agents: local MCP, exact token budgets, and dependency-aware retrieval.
repo-graphrag-mcp AGENTS.md
Instructions for yumeiriowl/repo-graphrag-mcp, covering repo graphrag mcp usage guide, prerequisites, three tools, tool 1: graphcreate and tool 2: graphquery.
codesearch CLAUDE.md
Instructions for flupkede/codesearch, a project described as: Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.