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/MrUversky/devhub-coreWrote 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/mruversky/devhub-core/devhub)<a href="https://agentmods.dev/rules/mruversky/devhub-core/devhub"><img src="https://agentmods.dev/badge/rules/mruversky/devhub-core/devhub/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/mruversky/devhub-core/devhub"><img src="https://agentmods.dev/badge/rules/mruversky/devhub-core/devhub.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 | $0.00023 | $0.00414 |
| Opus 5.5 | $0.00009 | $0.00166 |
| Sonnet 5.5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
devhub 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 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.
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
DevHub workflow
When the user asks to find, understand, register, sync, recover, or review a project or service:
- For “set up my DevHub”, “connect everything I can access”, “Build my map”, or “refresh my DevHub”, first require the user-wide
devhub doctor --workflow --jsoncontract, then start withdevhub setup --json. The rule and MCP do not install this CLI. If it is absent, stop before provider I/O with DevHub needs an update and use only the approved pinned installer/checksum/release-evidence path after the user chooses Help me update DevHub. Never usenpm -g,sudoor a checkout symlink. Detection checks only local CLI and config markers; never treat it as authorization, account access, or a catalog fact. - Use the configured read-only DevHub MCP tools to search for an existing project and service before proposing a new record.
- Inspect only the current workspace and explicitly reviewed runtime evidence. Do not scan arbitrary ports, accounts, or networks.
- Keep project-owned native manifests separate from private DevHub overlays. Never modify a shared or external repository to add private operational metadata.
- Treat missing or stale evidence as unknown. Never claim a service is monitored, secure, recoverable, or inexpensive without reviewed evidence.
- Never put tokens, passwords, cookies, connection strings, private keys, or credential-bearing URLs in DevHub manifests, prompts, logs, or Git.
- MCP is read-only. Connected setup is also read-only. Prepare a minimal catalog diff through the DevHub CLI or registry checkout, validate it, and wait for explicit review before apply, commit, publish, restart, rollback, or any production action.
- Finish by explaining what is known, what remains unknown, and the next safe action.
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 First seen · 18 lines · 23 tokens per session scan A cc1defd91e52
devhub is a cursor rule published in the GitHub repository MrUversky/devhub-core (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 414 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
no-mvn-compile
Do not run mvn compile; rely on IDE lint errors.
backend
You are an expert in Go, Gin, Gorm, Gen, Cosy (https://cosy.uozi.org/) with a deep understanding of best practices and performance optimization techniques in these technologies.
gsd-ship-labels
After /gsd-ship creates a PR, always run gsd-ship-post (labels + optional changeset).
backend-python
Cursor rule "backend-python" from coeusyk/inference-x, covering backend python rules, stack assumptions, code style, fastapi conventions and schema conventions.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.