RUDR9: Instructions file for Codex

AGENTS.md

RUDR9 AGENTS.md is an instructions file for Codex, OpenCode from ardhaecosystem/RUDR9. It costs 544 tokens per session, scanned A, original, MIT.

Repository instructions for RUDR9, an installer that turns Hermes Agent into a nine-role AI engineering organization. They describe its role profiles, authority controls, workflow files, hooks, plugins, and testing commands.

In plain words
What is it for?
Use them to inspect or develop the installer, test role permissions and guard rules, run a no-change installation check, or perform the Docker-based test.
Why use it?
They explain the installer’s structure and provide safe dry-run and test procedures before applying its changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is ardhaecosystem/RUDR9's own configuration. It tells Codex and OpenCode how to work on RUDR9 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RUDR9 configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/rudr9/RUDR9.

Reuse

Borrowing it

Nothing to install: this file belongs to ardhaecosystem/RUDR9. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ardhaecosystem/RUDR9/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ardhaecosystem/RUDR9

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for RUDR9 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ardhaecosystem/rudr9/agents-md/github.svg)](https://agentmods.dev/instructions/ardhaecosystem/rudr9/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ardhaecosystem/rudr9/agents-md"><img src="https://agentmods.dev/badge/instructions/ardhaecosystem/rudr9/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for RUDR9 AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ardhaecosystem/rudr9/agents-md"><img src="https://agentmods.dev/badge/instructions/ardhaecosystem/rudr9/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 544 This file is loaded in full into every session.
When invoked 544 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00544 $0.00544
Opus 5.5 $0.00218 $0.00218
Sonnet 5.5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured 2mo ago against content hash 71e7f5cf3934, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RUDR9 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 2mo 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.

AGENTS.md · 55 lines

What it actually says

RUDR9

What This Is

One-command installer that transforms Hermes Agent into a 9-role AI engineering organization. Profiles, Kanban coordination, per-profile authority enforcement, PAUL-inspired workflow.

Repo Layout

  • install.sh — the installer (preflight → profiles → SOULs → toolsets → skills → MCPs → Kanban → hooks → plugin → verify)
  • assets/souls/ — 8 SOUL.md role templates
  • assets/plugins/rudr9-guard/ — authority enforcement plugin (pre_tool_call hook)
  • assets/hooks/rudr9-long-task/ — stuck loop alert
  • assets/templates/ — project init files (AGENTS.md, PROJECT.md, STATE.md)
  • Dockerfile — isolated test environment

Development

# Dry run (no changes)
./install.sh --dry-run

# Guard plugin tests
cd assets/plugins/rudr9-guard
python3 -c "
import sys; sys.path.insert(0, '.')
from rules import is_allowed
assert not is_allowed('planner', 'write_file')
assert is_allowed('builder', 'write_file')
assert not is_allowed('security', 'terminal')
print('ok')
"

# Full Docker test
docker build -t rudr9-test .
docker run -d --name rudr9-test rudr9-test tail -f /dev/null
docker exec -d rudr9-test bash -lc 'cd /home/rudr9/RUDR9 && ./install.sh > /tmp/install.log 2>&1'
# wait ~8 min
docker exec rudr9-test bash -lc 'hermes profile list && hermes kanban assignees'
docker rm -f rudr9-test

Conventions

  • Conventional Commits: feat:, fix:, docs:, refactor:
  • Branch naming: feat/, fix/, docs/
  • All changes through PRs — no direct commits to main
  • Test before pushing: ./install.sh --dry-run must pass

Key Design Decisions

  • Guard plugin reads HERMES_PROFILE env var (set by Kanban dispatcher when spawning workers) — NOT HERMES_HOME basename
  • Builder+Checker fused into one profile (in-session validation loop)
  • Kanban is coordination bus + user dashboard (not just display)
  • Sequential-by-default (max_in_progress_per_profile: 1) — parallelism is opt-in
  • Install backs up SOUL.md before overwriting; uninstall restores
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. 2mo ago First seen · 55 lines · 544 tokens per session scan A 71e7f5cf3934

Subscribe to this mod's changes

RUDR9 AGENTS.md is an instructions file published in the GitHub repository ardhaecosystem/RUDR9 (48 stars, last pushed 3mo ago), licensed MIT. It adds 544 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

Related

RUDR9 AGENTS.md compared with instructions from other repositories

RUDR9 AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
RUDR9 AGENTS.mdardhaecosystem/RUDR9Instructions file483mo agoMITA544Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode