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/kpolley/redai/agents-mdgit clone --depth 1 https://github.com/kpolley/redaiWrote 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/kpolley/redai/agents-md)<a href="https://agentmods.dev/instructions/kpolley/redai/agents-md"><img src="https://agentmods.dev/badge/instructions/kpolley/redai/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 | $0.00890 | $0.00890 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
redai 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Overview
RedAI is a Bun/TypeScript TUI for AI-assisted vulnerability scanning and validation. It scans source directories, uses Claude Code or Codex SDK agents for threat modeling and finding generation, and runs validator plugins against prepared browser or iOS simulator environments.
Code Map
src/tui/— Ink UI, screens, keyboard handling, and runtime state hooks.src/domain/— Zod schemas and shared domain types.src/pipeline/— run lifecycle, persistence, preflight, and the staged scan pipeline.src/analysis/— source language detection, tree-sitter wiring, and symbol/regex extraction (the "analysis units" step).src/scanner/— source context loading, scanner provider implementations, and scanner prompts.src/planner/— validation planning and matching findings to validator environments.src/validators/— validator plugins (browser, iOS simulator) and thevalidator-plugin.tsinterface.src/agents/— provider adapters.claude/andcodex/hold agent-session wrappers;anthropic/andopenai/hold structured-output helpers;agent-runner.tsis the shared runner entry.src/artifacts/andsrc/reporting/— persisted run artifacts and Markdown/JSON report generation.src/config/— local environment loading (.env).src/utils/— shared helpers.
Commands
bun install— install dependencies.bun run redai(orbun run dev) — launch the TUI.bun run typecheck—tsc --noEmit.
Invariants
Hard rules. Don't relax these without discussion.
- Bun only. Do not add an alternate package manager lockfile.
- Don't mutate target source. Scanner and validator agents must not edit files in the directory being analyzed.
- Artifacts go to
~/.redai/. Generated PoCs, helper scripts, logs, screenshots, and notes must be saved under~/.redai/runs/<runId>/— never written into the target source tree. - Persisted and cross-module shapes go through Zod in
src/domain/.
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 · 64 lines · 890 tokens per session scan A 8a42cf982e21
redai AGENTS.md is an instructions file published in the GitHub repository kpolley/redai (341 stars, last pushed 4mo ago), licensed MIT. It adds 890 tokens to every session, about $0.0044 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
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).
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.
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.
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.
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).
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.