runner CLAUDE.md

Project instructions for a .NET tool that runs coding-agent command-line programs such as Claude Code, Codex, Copilot, and Gemini.

In plain words
What is it for?
They guide work on securely starting these programs, streaming their events, tracking their lifecycles, and recording usage limits.
Why use it?
They give the agent a single project guide while keeping detailed information in the documentation, reducing confusion about how the project should be handled.

Instructions file

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/claude-md
Clone the repo
git clone --depth 1 https://github.com/agent-orc/runner
Per session 33 This file is loaded in full into every session.
When invoked 33 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 $0.00033 $0.00033
Opus 5 $0.00016 $0.00016
Sonnet 5 $0.00007 $0.00007
Haiku 4.5 $0.00003 $0.00003

Measured 2d ago against content hash f57da6392d9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runner CLAUDE.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.

CLAUDE.md · 5 lines

What it actually says

See AGENTS.md.

This project keeps a single, slim agent guide there; all detail lives in docs/.

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. 2d ago First seen · 5 lines · 33 tokens per session scan A f57da6392d9d

Subscribe to this mod's changes

runner CLAUDE.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 33 tokens to every session, about $0.0002 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.