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/bharath03-a/gitcortex/agents-mdgit clone --depth 1 https://github.com/bharath03-a/GitCortexWhat 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 | $0.00764 | $0.00764 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
GitCortex 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitCortex - Codex Guide
What This Repo Is
GitCortex (gcx) is a local-first, branch-aware code knowledge graph for Git repositories. It indexes changed files with tree-sitter, stores graph data in embedded KuzuDB, and exposes graph queries to AI coding assistants through MCP and the gcx CLI.
Workspace Layout
crates/gitcortex-core: shared schema, graph types, andGraphStoretrait. No I/O, no async.crates/gitcortex-indexer: sync tree-sitter parsers and incremental indexing.crates/gitcortex-store: KuzuDB backend implementingGraphStore.crates/gitcortex-mcp: MCP server and async boundary.crates/gitcortex-cli:gcxCLI commands.crates/gitcortex-viz: Rust-side viz embedding support.viz: React/Vite graph UI.tests/integration/fixtures: small language fixtures..gitcortex: repo-level GitCortex config and generated context.
Architecture Rules
gitcortex-coremust stay pure: no filesystem, subprocesses, network, or async.gitcortex-indexerandgitcortex-storeare sync-only.tokiobelongs only ingitcortex-mcpand CLI/server boundaries.- Store behavior goes through the
GraphStoretrait; do not make indexer or MCP depend on concrete Kuzu details unless that layer owns the concern. - Library code in
core,indexer, andstoreshould not introduce.unwrap()or.expect(). Propagate errors with the crate error type. - Hook and incremental-index paths must stay fast. Avoid broad scans, unbounded allocations, and expensive work on every git operation.
- Keep changes surgical. Do not refactor adjacent code unless it is required for the task.
GitCortex Graph Use
This repo is intended to be indexed by GitCortex. Use the compact GitCortex MCP server first for structural questions; it exposes one dispatch tool (gcx) so Codex gets graph access without loading the full tool-schema surface. Read source files after the graph narrows the search.
Useful commands:
gcx query search <fragment>
gcx query lookup-symbol <name>
gcx query find-callers <name>
gcx query find-callees <name>
gcx query list-definitions <path>
gcx query wiki <name>
gcx query tour --limit 12
gcx blast-radius --base main --head HEAD --format text
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 · 81 lines · 764 tokens per session scan A bf05d9c004a9
GitCortex AGENTS.md is an instructions file published in the GitHub repository bharath03-a/GitCortex (7 stars, last pushed 2d ago), licensed MIT. It adds 764 tokens to every session, about $0.0038 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
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.
buildNext
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
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
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.