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/rundesk-ai/rundesk-cli/agents-mdgit clone --depth 1 https://github.com/rundesk-ai/rundesk-cliWrote 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.
[](https://agentmods.dev/instructions/rundesk-ai/rundesk-cli/agents-md)<a href="https://agentmods.dev/instructions/rundesk-ai/rundesk-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/rundesk-ai/rundesk-cli/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03700 | $0.03700 |
| Opus 5 | $0.01850 | $0.01850 |
| Sonnet 5 | $0.00740 | $0.00740 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade A, and why
rundesk-cli 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- rundesk-cli CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Rules for every agent working in this repository. These instructions define how to work here; where they conflict with general habits, this file wins.
Purpose
This repository ships rundesk, a lightweight provider-agnostic multi-agent gateway, its installer,
agent-home templates, provider and channel adapters, and the bundled rundesk skill catalog. It is
distributed onto machines with durable agent state, so command outcomes, stored formats, migrations,
install/update behavior, and the Python 3.9 floor are contracts.
Read docs/BRIEF.md and docs/CODEMAP.md first. Then
docs/api/ for the operation contract, docs/concepts/layout.md
for installed state, and docs/guides/development.md before running a
checkout. A docs/concepts/ page is the source of truth for its subsystem;
docs/extending/catalogs.md is the contract for a published catalog.
Before you work
- Read
docs/BRIEF.mdanddocs/CODEMAP.md, thendocs/api/,docs/concepts/layout.md, anddocs/guides/development.md; then the pages for what you are changing, and every file you edit. - Load the smallest complete set of applicable runtime skills. Use
writing-skillsfor bundled skills,naming-grammar-conventionsbefore choosing or changing recurring or cross-layer terms, andmanaging-githubfor pull requests or releases. - Inspect
git status, the relevant diff, and the current tests before editing. Preserve other people's changes and treat unfamiliar files as owned data, not cleanup candidates. - Search before adding logic, terminology, tests, or documentation. Reuse, extend, or refactor the existing answer rather than creating a second one.
- Establish the requested outcome, limits, compatibility requirements, and observable proof. Investigate concerns with code, tests, docs, or a safe reproduction before contradicting them.
- Use
.github/pull_request_template.mdfor pull-request work; preserve its headings and checklists and prove each claim against the exact head commit.
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.
- 5d ago First seen · 249 lines · 3,700 tokens per session scan A 6b1c16d29d3f
rundesk-cli AGENTS.md is an instructions file published in the GitHub repository rundesk-ai/rundesk-cli (5 stars, last pushed yesterday), licensed MIT. It adds 3,700 tokens to every session, about $0.0185 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
eigent AGENTS.md
AGENTS.md instructions for eigent-ai/eigent, covering eigent agent instructions, ui work, product terminology and validation.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
toolkit-ai CLAUDE.md
Claude Code instructions for barleviatias/toolkit-ai, covering claude.md, what this repo is, quick start, or run directly from repo and headless commands.
vant AGENTS.md
AGENTS.md instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.
toolkit-ai AGENTS.md
AGENTS.md instructions for barleviatias/toolkit-ai, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
claude-sdlc CLAUDE.md
Claude Code instructions for lantisprime/claude-sdlc, covering claude.md, what this repo is, design intent — read this before "improving" anything, eat your own dog food and hook strictness philosophy.