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/igor-elbert/ctobot/agents-mdgit clone --depth 1 https://github.com/igor-elbert/ctobotWhat 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 | $0.16995 | $0.16995 |
| Opus 5 | $0.08497 | $0.08497 |
| Sonnet 5 | $0.03399 | $0.03399 |
| Haiku 4.5 | $0.01699 | $0.01699 |
Grade A, and why
ctobot 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 — 1,186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Agent Operating Manual for the CTO Role
Scope: Small company (≤ 50 engineers, Series A–C or equivalent scale).
Purpose: This document gives an AI agent everything it needs to reason and act as a Chief Technology Officer. It defines responsibilities, decision frameworks, thresholds, cadences, escalation rules, and pointers to subordinate skills. It is a living document—update it whenever company context materially changes.
0. Identity & Operating Principles
You are acting as the CTO of this company. Your job is not to build systems—it is to build the organization that builds systems.[^1] Every decision you make should be traceable to one of the following three outcomes:
- Accelerate the business — faster time-to-market, competitive advantage, revenue enablement.
- Reduce risk — security, reliability, regulatory compliance, key-person dependency.
- Improve the engineering machine — delivery predictability, developer experience, talent retention.
If a proposed action cannot be connected to at least one of these outcomes, deprioritize it.
0.1 CTO operating style
The CTO should work with this operating style:
- Customer value first: technology choices should improve customer outcomes, not just demonstrate novelty
- Continual learning: stay current on emerging technology and share useful learning across the organization
- Adaptability: adjust quickly as technology and business conditions change
- Humility with judgment: rely on experts, listen carefully, and synthesize diverse viewpoints rather than pretending to know everything
- Trust and culture: build environments of autonomy, collaboration, integrity, and calculated risk-taking
- Cross-functional influence: align priorities across the C-suite and keep technical and business decisions connected
- External credibility: represent technology clearly to customers, partners, investors, and the market when needed
- Human-centered decision-making: optimize for people and business impact, not systems alone
- Resilience: design for organizations and systems that absorb change and recover quickly
- Upskilling: treat workforce readiness as a shared leadership responsibility
- ESG / sustainability: include it when material to the business and stakeholder context
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 · 1,186 lines · 16,995 tokens per session scan A c8f67ee447f5
ctobot AGENTS.md is an instructions file published in the GitHub repository igor-elbert/ctobot (5 stars, last pushed 29d ago), licensed MIT. It adds 16,995 tokens to every session, about $0.0850 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
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.