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/consiliency/code-index-mcp/agents-mdgit clone --depth 1 https://github.com/Consiliency/Code-Index-MCPWhat 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 | $0.04845 | $0.04845 |
| Opus 5 | $0.02423 | $0.02423 |
| Sonnet 5 | $0.00969 | $0.00969 |
| Haiku 4.5 | $0.00485 | $0.00485 |
Grade A, and why
Code-Index-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 2d 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 — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Agent Configuration
This file defines the capabilities and constraints for AI agents working with this codebase.
Current State
System Complexity: 5/5 (High — SQLite FTS5 + Qdrant vector index, 48 language plugins, rerankers, query-intent routing)
MCP Status: Use MCP indexed search when repository readiness is ready; STDIO is the primary surface
Last Updated: 2026-04-23
Support matrix: Customer-facing language/runtime support claims live in docs/SUPPORT_MATRIX.md.
Dependency truth: Use uv sync --locked; pyproject.toml and uv.lock are canonical.
Beta status: Multi-repo support and the STDIO interface are in beta. STDIO is the primary surface for LLM tool calls; FastAPI is a secondary admin surface for diagnostics and manual operations. Expect API surface changes before stable release.
Public alpha repository model: v3 supports many unrelated repositories on one machine, with one registered worktree per git common directory. Only the tracked/default branch is indexed automatically. Indexed results are authoritative only when readiness is
ready; unavailable indexes returnindex_unavailablewithsafe_fallback: "native_search".
What's Actually Implemented
- ✅ STDIO transport (
search_code,symbol_lookup,summarize_sample,reindexMCP tools) - ✅ FastAPI admin surface with endpoints:
/symbol,/search,/status,/plugins,/reindex - ✅ Dispatcher with caching and auto-initialization
- ✅ Python plugin fully functional with Tree-sitter + Jedi
- ✅ JavaScript/TypeScript plugin fully functional with Tree-sitter
- ✅ C plugin fully functional with Tree-sitter
- ✅ SQLite persistence layer with FTS5 search
- ✅ File watcher auto-starts in
initialize_services()after dispatcher is ready; stopped inmain()finally block on exit (EnhancedDispatcher mode only) - ✅ Error handling and logging framework
- ✅ Comprehensive testing framework (pytest with fixtures)
- ✅ CI/CD pipeline with GitHub Actions
- ✅ Docker support and build system
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.
- 2d ago First seen · 434 lines · 4,845 tokens per session scan A 64d7e2503a0c
Code-Index-MCP AGENTS.md is an instructions file published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It adds 4,845 tokens to every session, about $0.0242 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
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).
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
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
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.