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/rmednitzer/relay-shell/agents-mdgit clone --depth 1 https://github.com/rmednitzer/relay-shellWrote 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/rmednitzer/relay-shell/agents-md)<a href="https://agentmods.dev/instructions/rmednitzer/relay-shell/agents-md"><img src="https://agentmods.dev/badge/instructions/rmednitzer/relay-shell/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 | $0.01490 | $0.01490 |
| Opus 5 | $0.00745 | $0.00745 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade B, and why
relay-shell AGENTS.md scanned grade B with 1 finding 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
3. **Preserve capability.** Do not reduce shell/SSH/root/sudo viability unless explicitly requested. How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is designed for AI-assisted operations and development. This file defines the required behavior for any coding/ops agent working in this repo.
1) Mission
relay-shell is an MCP server for high-capability local shell and SSH operations
with strong auditability and bounded execution. The project goals are:
- Maximum useful operator capability (including privileged/root workflows when required)
- Reliable execution and error containment
- Audit-first observability
- Reasonable, explicit security controls without disabling core capability
2) Non-negotiable operating principles
- Never bypass auditability intentionally.
- Never introduce hidden execution paths. All tool paths must remain visible and auditable.
- Preserve capability. Do not reduce shell/SSH/root/sudo viability unless explicitly requested.
- Prefer explicit bounded behavior. Timeouts, output limits, and session caps must remain enforced.
- Fail closed where practical, fail safe everywhere else. Denials must be explicit; failures must not crash transport.
3) Trusted baseline references
Use these as decision anchors for changes:
- Model Context Protocol docs: https://modelcontextprotocol.io
- GitHub Actions hardening: https://docs.github.com/actions/security-guides/security-hardening-for-github-actions
- GitHub CodeQL: https://docs.github.com/code-security/code-scanning/introduction-to-code-scanning/about-code-scanning-with-codeql
- GitHub dependency review: https://docs.github.com/code-security/supply-chain-security/understanding-your-software-supply-chain/about-dependency-review
- OWASP Logging Cheat Sheet: https://cheatsheetseries.owasp.org/cheatsheets/Logging_Cheat_Sheet.html
- OWASP Secrets Management Cheat Sheet: https://cheatsheetseries.owasp.org/cheatsheets/Secrets_Management_Cheat_Sheet.html
4) Implementation standards
Reliability
- Keep tool responses deterministic and bounded.
- Do not allow uncaught exceptions to escape tool boundaries.
- Preserve current behavior: return structured text errors instead of transport failures.
- Add/adjust tests with any behavior change.
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.
- 3d ago First seen · 114 lines · 1,490 tokens per session scan B 6f817aaaa8fa
relay-shell AGENTS.md is an instructions file published in the GitHub repository rmednitzer/relay-shell (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,490 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Containarium CLAUDE.md
Claude Code instructions for FootprintAI/Containarium, covering containarium — guidance for claude / ai assistants, no instance / endpoint / tenant names in oss-visible files, cli-first, mcp wraps it, api: protobuf contract first, grpc-gateway for rest and strong typing — use the type system, not strings.
vibeshell AGENTS.md
AGENTS.md instructions for veithly/vibeshell, covering vibeshell — agent guide, architecture, critical knowledge, russh 0.44 constraints and frontend → backend communication.
mcp-ssh CLAUDE.md
Instructions for AiondaDotCom/mcp-ssh, covering claude.md, project overview, development commands, basic operations and development scripts.
winkterm AGENTS.md
Instructions for Cznorth/winkterm, covering agents.md, project overview, common commands, backend development and start the development server.
hop CLAUDE.md
Instructions for danmartuszewski/hop: Use conventional commit format with imperative mood.
tunnel-manager AGENTS.md
AGENTS.md instructions for Knuckles-Team/tunnel-manager, covering agents.md, tech stack & architecture, architecture diagram, workflow diagram and commands (run these exactly).