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.
git clone --depth 1 https://github.com/olgasafonova/mediawiki-mcp-serverWrote 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/rules/olgasafonova/mediawiki-mcp-server/wiki-safety)<a href="https://agentmods.dev/rules/olgasafonova/mediawiki-mcp-server/wiki-safety"><img src="https://agentmods.dev/badge/rules/olgasafonova/mediawiki-mcp-server/wiki-safety/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/rules/olgasafonova/mediawiki-mcp-server/wiki-safety"><img src="https://agentmods.dev/badge/rules/olgasafonova/mediawiki-mcp-server/wiki-safety.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 | $0.00208 | $0.00208 |
| Opus 5 | $0.00104 | $0.00104 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
wiki-safety 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 11d 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.
What it actually says
Wiki editing safety guardrails
- Always use
preview=truebefore executingmediawiki_find_replace,mediawiki_bulk_replace, ormediawiki_apply_formatting. Show the preview and get user confirmation. - Don't guess page titles; they are case-sensitive. Use
mediawiki_resolve_titlewhen the exact title is uncertain. - Use internal wiki links
[[Page Title]]or[[Page Title|Display Text]], never full URLs for internal wiki pages. - Provide clear edit summaries explaining what changed and why.
- Use
mediawiki_search_in_pageto find text within a known page instead of fetching the entire page. - Don't create names as email links (
[[mailto:...|Name]]); wiki doesn't render these properly. Use "Name (email)" format instead. - For outdated content, add
{{Expired}}at the top and[[Category:Expired]]at the bottom rather than deleting.
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.
- 11d ago First seen · 14 lines · 208 tokens per session scan A 84ec2887fe66
wiki-safety is a cursor rule published in the GitHub repository olgasafonova/mediawiki-mcp-server (20 stars, last pushed 2d ago), licensed MIT. It adds 208 tokens to every session, about $0.0010 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 2026-08-30.
Other cursor rules, from other repositories
miro-best-practices
MCP server for controlling Miro whiteboards with AI assistants.
agentic-loop
Vault agentic develop→validate loop — follow on every coding task.
architecture
Core file-system logic stays UI-agnostic; platform-specific quirks stay behind an adapter per OS.
unit-tests-tdd
TDD for behavior changes; co-located tests; keep touched areas well covered.
minimal-communication
Minimal-communication response style — facts only, no validation, small phrases. Always active.
go-project-structure
This rule ensures that Go projects follow a consistent and idiomatic structure, making the codebase easier to navigate, maintain, and scale.