Borrowing it
Nothing to install: this file belongs to quazardous/nelson-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/quazardous/nelson-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/quazardous/nelson-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/quazardous/nelson-mcp/agents-md)<a href="https://agentmods.dev/instructions/quazardous/nelson-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/quazardous/nelson-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/quazardous/nelson-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/quazardous/nelson-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 | $0.03448 | $0.03448 |
| Opus 5.5 | $0.01379 | $0.01379 |
| Sonnet 5.5 | $0.00690 | $0.00690 |
| Haiku 4.5 | $0.00345 | $0.00345 |
Grade C, and why
nelson-mcp AGENTS.md scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> `unopkg remove org.extension.nelson` → `rm -rf $PROFILE/user/uno_packages/cache How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Quickstart cheatsheet for AI agents
[!IMPORTANT] Update this file after making nontrivial changes.
Project
Nelson MCP — LibreOffice extension (Python/UNO) exposing document tools via MCP server.
Where is what
plugin/main.py Entry point, bootstrap
plugin/version.py Version (single source of truth)
plugin/plugin.yaml Global config schema
plugin/_manifest.py Generated — do not edit
plugin/framework/ Core engine (services, tools, events, config, http, dialogs)
plugin/modules/<name>/ Feature modules (module.yaml + __init__.py + tools/ + services/)
extension/ Static LO files (XCU, manifest, assets)
scripts/ Build & deploy scripts
tests/ Pytest suite (must pass — 'make test' is a gate)
Makefile All build/dev targets
install.ps1 / install.sh Dev environment setup (installs bash, make, pyyaml, vendor deps)
Setup & dev loop
./install.ps1 # Windows: installs deps (bash, make, pyyaml, vendor)
./install.sh # Linux/macOS equivalent
make build # Build .oxt
make deploy # Build + reinstall + restart LO + show log
make log # Show ~/nelson.log
make test # Pytest
make set-config # List all config keys
make help # All targets
AI agent note:
make deploytakes 60–120 seconds (kills LO, reinstalls extension, restarts LO, waits for bootstrap). Do not pipe its output (| tail,| grep) — this causes buffering freezes. Run it plain with a long timeout (300s+).
Under wbox (the usual agent loop) use the MCP tools instead, in this order — never deploy while soffice is running:
mcp__lo-wbox__kill → mcp__lo-wbox__deploy → mcp__lo-wbox__launch
The same loop is available from make, without MCP — offscreen by default,
WBOX_VISIBLE=1 to get a window:
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.
- 1mo ago Changed · +7 lines · +106 tokens per session a66b1e88f4cf
- 1mo ago Changed · +37 lines · +490 tokens per session a32338f0259c
- 2mo ago First seen · 215 lines · 2,852 tokens per session scan C 3128cc659a38
nelson-mcp AGENTS.md is an instructions file published in the GitHub repository quazardous/nelson-mcp (41 stars, last pushed 3d ago), licensed MPL-2.0. It adds 3,448 tokens to every session, about $0.0138 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
nelson-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nelson-mcp AGENTS.mdquazardous/nelson-mcp | Instructions file | 41 | 3d ago | MPL-2.0 | C | 3,448 | 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 |