runner AGENTS.md

A short guide for CodingAgentRunner, a .NET library that starts coding-agent command-line programs such as Claude Code, Codex and Gemini as child processes.

In plain words
What is it for?
Use it when working on the library, understanding how agent runs finish or stop, investigating Windows process handling, or editing user-facing text.
Why use it?
It points developers to the documents that explain the library’s design, process outcomes and Windows safeguards, while keeping those details out of the guide.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/agent-orc/runner/agents-md
Clone the repo
git clone --depth 1 https://github.com/agent-orc/runner

Made for: Codex, OpenCode.

Per session 356 This file is loaded in full into every session.
When invoked 356 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00356 $0.00356
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash f2d021b8dadd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runner 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 yesterday.

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 · 29 lines

What it actually says

Agent guide

CodingAgentRunner is a .NET library that runs coding-agent CLIs (Claude Code, Codex, Gemini, Antigravity) as child processes. This file is intentionally short. The detail lives in docs/ — read it there rather than duplicating it here.

Read these

Rules

  • The platform owns git. Do not run git commit or git push. The host application owns version control.
  • Follow docs/voice-and-messaging.md for any user-facing text.
  • Hardening ships with tests. Each hardening behaviour links to the incident that motivated it and is pinned by a test. Don't remove a guard without understanding the reason behind it — see docs/why-windows-hardening.md.
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. yesterday First seen · 29 lines · 356 tokens per session scan A f2d021b8dadd

Subscribe to this mod's changes

runner AGENTS.md is an instructions file published in the GitHub repository agent-orc/runner (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 356 tokens to every session, about $0.0018 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.