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/agent-orc/runner/agents-mdgit clone --depth 1 https://github.com/agent-orc/runnerWhat 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 | $0.00356 | $0.00356 |
| Opus 5 | $0.00178 | $0.00178 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
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.
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
- docs/README.md — index of the developer wiki.
- docs/architecture.md — the modules and the public API.
- docs/why-windows-hardening.md — why each hardening behaviour exists; each ships with a test.
- docs/process-termination.md — the outcome model
(
completed/stopped/failed) and the run lifecycle. - docs/voice-and-messaging.md — how to write about this project: plain statements, no marketing language. Read this before editing the README, the website, or any user-facing text.
Rules
- The platform owns git. Do not run
git commitorgit 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.
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.
- yesterday First seen · 29 lines · 356 tokens per session scan A f2d021b8dadd
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.
Other instructions, from other repositories
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
Circus-Chief CLAUDE.md
Instructions for ferrislucas/Circus-Chief, covering claude.md, project overview, common commands, development - start both frontend and backend and run all unit tests.
stealth-code CLAUDE.md
Instructions for suxrobGM/stealth-code, covering stealthcode, build & run, architecture, project structure and key conventions.
code-meridian AGENTS.md
Instructions for Driftya/code-meridian, covering agents.md, behavior expectations, required codemeridian usage, trigger rules and repository rules.
cupcake CLAUDE.md
Instructions for eqtylab/cupcake, covering cupcake system overview, policy engine (wasm/rego) details, 1. routing vs. policy execution (critical), 2. opa rego v1 migration (critical) and 3. decisions & synthesis.
code-meridian copilot-instructions.md
Instructions for Driftya/code-meridian: Read AGENTS.md — it is the single source of truth for architecture, conventions, tool usage triggers, and contribution rules for this repository.