Repo-Interrogator: Instructions file for Codex

AGENTS.md

Repo-Interrogator AGENTS.md is an instructions file for Codex, OpenCode from taggedzi/Repo-Interrogator. It costs 2,111 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working with Repo-Interrogator, a local tool that indexes and searches one code repository without changing its files.

In plain words
What is it for?
They help agents use repository memory to find symbols, callers, dependencies, and entry points; narrow the files they inspect; and follow the repository’s decision rules and architecture records.
Why use it?
They give agents rules for understanding a repository safely and consistently before making decisions or edits.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is taggedzi/Repo-Interrogator's own configuration. It tells Codex and OpenCode how to work on Repo-Interrogator 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 Repo-Interrogator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to taggedzi/Repo-Interrogator. 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/taggedzi/Repo-Interrogator/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/taggedzi/Repo-Interrogator

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 Repo-Interrogator AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/taggedzi/repo-interrogator/agents-md.svg)](https://agentmods.dev/instructions/taggedzi/repo-interrogator/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/taggedzi/repo-interrogator/agents-md"><img src="https://agentmods.dev/badge/instructions/taggedzi/repo-interrogator/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,111 This file is loaded in full into every session.
When invoked 2,111 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 $0.02111 $0.02111
Opus 5 $0.01056 $0.01056
Sonnet 5 $0.00422 $0.00422
Haiku 4.5 $0.00211 $0.00211

Measured 7d ago against content hash a4243a1fd7c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Repo-Interrogator 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 7d 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 · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the operational guide for AI coding agents (Codex, Codex CLI, Cursor agents, etc.) working in this repository.

This project implements a local-first, deterministic MCP server that allows AI clients to interrogate a single code repository in a safe, auditable, and structured way. The server exposes tools for indexing, searching, outlining, and context bundling — not for modifying code.

If anything in this file conflicts with SPEC.md, SPEC.md is the source of truth.


Agent Instructions

Use codebase-memory-mcp as the first tool for understanding this repository.

Before doing broad file reads, grep searches, or architecture exploration:

  • Query codebase-memory-mcp for relevant files, symbols, callers, callees, dependencies, and entry points.
  • Use graph results to narrow the search area.
  • Only read full files after identifying likely relevant targets.

Prefer codebase-memory-mcp for:

  • finding where a function/class/module is defined
  • finding callers and callees
  • tracing execution paths
  • identifying entry points
  • understanding project structure
  • impact analysis before edits
  • detecting dead or disconnected code
  • summarizing architecture

Use direct file reads for:

  • editing code
  • checking exact implementation details
  • reviewing tests
  • inspecting config files
  • verifying behavior before making changes

When starting work in this repo:

  1. Check whether the project is indexed.
  2. Index or refresh the index if needed.
  3. Use graph queries before broad text searches.
  4. Keep context small by reading only the files needed for the current task.

When making changes:

  • Use codebase-memory-mcp to find affected callers/tests.
  • Read the exact files before editing.
  • Run the smallest relevant tests first.

Python environment

This project uses a Python virtual environment located at .venv/.

Rules:

  • The .venv/ directory is created and managed by the user.
  • Agents must not create, modify, delete, or replace virtual environments.
  • All Python commands (tests, linting, formatting, execution) must be run using the .venv/ environment.
  • If the environment is not active or unavailable, agents must stop and ask for guidance rather than guessing.

Read the full file on GitHub · 359 lines

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. 7d ago First seen · 359 lines · 2,111 tokens per session scan A a4243a1fd7c9

Subscribe to this mod's changes

Repo-Interrogator AGENTS.md is an instructions file published in the GitHub repository taggedzi/Repo-Interrogator (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,111 tokens to every session, about $0.0106 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.