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/jkudjo/oh-my-cursor/diagnosegit clone --depth 1 https://github.com/Jkudjo/oh-my-cursorWrote 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/jkudjo/oh-my-cursor/diagnose)<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/diagnose"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/diagnose.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.01042 |
| Opus 5 | $0.00007 | $0.00521 |
| Sonnet 5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
diagnose 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@diagnose
Trigger: Any bug, error, performance issue, or unexpected behavior where the cause is unknown.
The iron law
Root cause before fix. Never propose a solution until you have identified the cause with evidence.
Protocol
Phase 0 — Gather facts (read-only, max 3 min)
Before forming any hypothesis, collect:
- Exact symptom (error message, metric, user report — verbatim)
- When it started (specific time, after deploy, after config change)
- Scope (all users / one region / one endpoint / one query)
- What changed recently (deploy, config, data volume, traffic pattern)
Label everything: [FACT] (observed), [INFERRED] (reasoned), [UNKNOWN] (not yet knowable).
Phase 1 — Generate hypothesis tree (before investigating any)
Generate ≥5 hypotheses across all failure domains. Do not begin investigating until the full tree is built.
For each hypothesis, produce this structured entry:
H{N}: [specific cause]
Confidence: 0.XX (0.0 = ruled out, 1.0 = confirmed)
Cost to test: {minutes} / {read-only|config-check|query|trace|restart}
Signal value: high / medium / low
Evidence for: [what observations support this]
Evidence against: [what observations contradict this]
To confirm: [exact command, log pattern, or metric that would confirm]
To rule out: [exact command, log pattern, or metric that would eliminate]
Failure domains to cover:
- App: crash, exception, logic error, config mismatch, deploy regression
- Data: DB connectivity, slow query, lock contention, N+1, migration state, schema mismatch
- Network: DNS, timeout, connection pool exhaustion, firewall, load balancer, CDN edge
- Infra: pod restart, OOMKilled, node pressure, readiness probe, selector mismatch
- Dependencies: third-party API, queue backlog, auth service, feature flag state, cache
- Client/Observability: stale cache, client-side bug, wrong user segment, metrics blind spot
Phase 2 — Rank and budget
Sort hypotheses by: (confidence × signal value) ÷ cost to test
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 First seen · 113 lines · 14 tokens per session scan A 3b4634ba6b23
diagnose is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,042 once invoked, about $0.0001 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
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
general
You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.
refactoring
Refactoring: systematic approach, extract/inline, guard clauses, early returns.
create-rule-agent
This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…
cloudflare-workers-hono-auto
Cloudflare Workers with Hono framework development standards and best practices.