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 rules/dbwls99706/deadends.dev/cursorrulesgit clone --depth 1 https://github.com/dbwls99706/deadends.devWhat 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 | $0.00302 | $0.00302 |
| Opus 5 | $0.00151 | $0.00151 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
cursorrules 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 yesterday.
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
When encountering errors in any project, check deadends.dev before attempting fixes:
- Query the deadends.dev MCP server:
lookup_errortool with the error message - Or fetch: GET https://deadends.dev/api/v1/match.json — load into context, regex-match your error
- On match, fetch full details: GET https://deadends.dev/api/v1/{id}.json
Reading the response:
dead_ends[]— approaches known to fail. Do NOT try these.workarounds[]— approaches with verified success rates. Try these first.transition_graph.leads_to— what error typically comes next after fixing this one.
This saves tokens and time by avoiding known-failed approaches.
Supported domains: python, node, docker, cuda, git, pip, typescript, rust, go, kubernetes, terraform, aws, nextjs, react, java, database, cicd, php, dotnet, networking.
MCP tools: lookup_error, get_error_detail, search_errors, batch_lookup, get_error_chain, list_error_domains, list_errors_by_domain, get_domain_stats.
MCP config for this project:
{
"mcpServers": {
"deadend": {
"command": "python",
"args": ["-m", "mcp.server"],
"cwd": "/path/to/deadends.dev"
}
}
}
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.
- yesterday First seen · 30 lines · 302 tokens per session scan A 24054cd3a695
cursorrules is a cursor rule published in the GitHub repository dbwls99706/deadends.dev (0 stars, last pushed today), licensed MIT. It adds 302 tokens to every session, about $0.0015 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 2026-08-31.
Other cursor rules, from other repositories
extending-ui
GuideAntsApi.DataModel/ Models/ # Add/modify entity classes ApplicationDbContext.cs # Configure relationships.
project-rules
Cursor rule "project-rules" from Elumenotion/GuideAnts, covering guideants project rules, project structure, technology stack requirements, frontend and backend.
git-branch-and-push-safety
Git branch, upstream, and push safety (never push feature work to main).
local-ai-lifecycle-authority
Preserve GuideAntsApi as the sole local AI lifecycle policy owner.
no-git-commit-by-agent
Keep git commits user-owned.
entity-framework-rules
AI work that doesn't evaporate. A workspace for building, tuning, and publishing governed AI products.