Borrowing it
Nothing to install: this file belongs to bimwright/dwg-mcp. 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/bimwright/dwg-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/bimwright/dwg-mcpWrote 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/bimwright/dwg-mcp/agents-md)<a href="https://agentmods.dev/instructions/bimwright/dwg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bimwright/dwg-mcp/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/bimwright/dwg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bimwright/dwg-mcp/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 | $0.01641 | $0.01641 |
| Opus 5.5 | $0.00656 | $0.00656 |
| Sonnet 5.5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
dwg-mcp 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — dwg-mcp health and update contract
These instructions apply to dwg-mcp v2.1.2 and v2.1.1. Earlier v2.0.1 does not expose dwg_health.
Session startup
In writable mode, select the intended AutoCAD instance with dwg_list_available_targets then dwg_switch_target(target="pid:<PID>"); the default verification confirms the process and active drawing before writes. Changing an existing instance binding requires pid:/id:; leaving a live confirmed target also requires rebind=true. --target and verify=false select reads only. Reselecting the same process with verify=false removes write confirmation. The previous expected drawing lifetime ID is preserved unless rebind=true resets it or an explicit expected_document_id replaces it. After opening/switching drawings, inspect health; confirm a different drawing with its matching expected_document_id or rebind=true. Do not bypass AMBIGUOUS_TARGET, TARGET_LOST, TARGET_CHANGED or DOCUMENT_CHANGED. Gateway and plugin must both support target guards for writes.
In --read-only mode, dwg_switch_target is absent and direct calls are refused. Select the initial instance with --read-only --target pid:<PID> or --target id:acad-<year>-<PID>. On TARGET_LOST/TARGET_CHANGED, list the available targets and restart the gateway with the intended explicit --target; do not call the unavailable switch tool. The gateway never falls back to another instance.
Call dwg_health(check_updates=true) once at session start if network access is permitted; later routine probes remain offline. If network access is unavailable or disallowed, report not checked/unknown, never up to date.
Health is read-only, does not require or lock a drawing, and never creates, activates, saves or closes one. A successful host/state probe requires host_connected=true and ok=true. No target preserves the gateway identity. A responding legacy dispatcher may return HEALTH_UNSUPPORTED with host_connected=true, but health/state and the plugin's loaded identity remain unverified. A busy UI retains observed plugin identity and marks document state unavailable. Do not infer corruption, a closed host or missing installation from unavailable evidence.
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.
- 4d ago Changed · +7 tokens per session 09200a450e06
- 6d ago Changed · +11 lines · +659 tokens per session 528bb491433d
- 26d ago First seen · 44 lines · 975 tokens per session scan A 206979d270f5
dwg-mcp AGENTS.md is an instructions file published in the GitHub repository bimwright/dwg-mcp (27 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,641 tokens to every session, about $0.0066 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 2026-10-11.
dwg-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dwg-mcp AGENTS.mdbimwright/dwg-mcp | Instructions file | 27 | 5d ago | Apache-2.0 | A | 1,641 | 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 | today | 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 |