Borrowing it
Nothing to install: this file belongs to ryanlewis/exeslim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ryanlewis/exeslim/main/AGENTS.mdgit clone --depth 1 https://github.com/ryanlewis/exeslimWrote 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/ryanlewis/exeslim/agents-md)<a href="https://agentmods.dev/instructions/ryanlewis/exeslim/agents-md"><img src="https://agentmods.dev/badge/instructions/ryanlewis/exeslim/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.
<a href="https://agentmods.dev/instructions/ryanlewis/exeslim/agents-md"><img src="https://agentmods.dev/badge/instructions/ryanlewis/exeslim/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00288 | $0.00288 |
| Opus 5.5 | $0.00115 | $0.00115 |
| Sonnet 5.5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade B, and why
exeslim AGENTS.md scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
docker, nginx, Chrome. `apt` works, so `sudo apt-get install <pkg>` is fine for Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
It is a deployment target: a minimal base carrying systemd, TLS roots and curl, What it actually says
You are running in an exe.dev VM.
https://exe.dev/docs/proxy.md has details about the exe.dev HTTPS proxy.
Only use documented exe.dev features (see https://exe.dev/docs.md). Undocumented local endpoints are internal infrastructure—unstable and unsupported.
This VM runs exeslim, not exeuntu
It is a deployment target: a minimal base carrying systemd, TLS roots and curl, and nothing else. Do not assume the usual exeuntu toolbox is present.
Not installed: compiler/build-essential, python, node, Go, uv, git,
docker, nginx, Chrome. apt works, so sudo apt-get install <pkg> is fine for
anything you genuinely need — but prefer building artifacts elsewhere and
shipping them here, which is how this box is meant to be used.
Services are systemd units. Start/stop with systemctl, and read logs with
journalctl -u <name> — journald storage is persistent, and with no toolchain
on the box it is the main debugging surface.
The app is normally a prebuilt binary deployed by scp/rsync from a
laptop or CI, then restarted via systemd. Anything you install directly on the
VM is lost if it is recreated from a fresh image, so durable changes belong in
the deploying repo, not here.
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.
- 2mo ago First seen · 25 lines · 288 tokens per session scan B d9cbcc7f29bd
exeslim AGENTS.md is an instructions file published in the GitHub repository ryanlewis/exeslim (13 stars, last pushed 5d ago), licensed MIT. It adds 288 tokens to every session, about $0.0012 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
exeslim AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| exeslim AGENTS.mdryanlewis/exeslim | Instructions file | 13 | 5d ago | MIT | B | 288 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |