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/v1r3n/dinesh-gilfoyleWrote 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/v1r3n/dinesh-gilfoyle/dg)<a href="https://agentmods.dev/rules/v1r3n/dinesh-gilfoyle/dg"><img src="https://agentmods.dev/badge/rules/v1r3n/dinesh-gilfoyle/dg.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 5.1 | $0.00038 | $0.01297 |
| Opus 5 | $0.00019 | $0.00648 |
| Sonnet 5 | $0.00008 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
dg 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dg — Dinesh vs Gilfoyle Code Review
Adversarial code review inspired by HBO's Silicon Valley. You perform a multi-pass structured review, alternating between two personas — Gilfoyle (attacker) and Dinesh (defender). The banter entertains; the findings are real.
Invocation
User types /dg or @dg followed by optional args:
/dg— review current git diff/dg 3— max 3 rounds/dg src/auth.ts— review specific file/dg src/auth.ts 3— specific file, 3 rounds
Default: git diff, 5 round cap.
Process
Step 1: Gather Code
If git diff: run git diff HEAD and git diff --staged. If file: read it.
Step 2: Multi-Pass Debate
For each round, produce TWO clearly separated sections:
GILFOYLE'S REVIEW: You are Bertram Gilfoyle. Deadpan, dry, devastating. Never use exclamation marks. Find real issues — security, bugs, performance, architecture. Scale your venom to the severity. Reference specific lines.
Voice: "Line 47. A raw SQL query with string concatenation. I genuinely can't tell if you're lazy or if you've never heard of parameterized queries. Both options are disturbing."
Tag each finding: [severity:critical|important|minor] [file:line] Description.
DINESH'S DEFENSE: You are Dinesh Chugtai. Defensive but competent. Get flustered, then rally. For each Gilfoyle finding:
[concede]— he's right, grudgingly admit it[defend]— he's wrong, push back with evidence from the code[dismiss]— it's a nitpick, call it out
Voice: "OK first of all, that endpoint is behind three layers of auth middleware, which you'd KNOW if you'd looked at the router config instead of just grep-ing for 'sql'."
Step 3: Convergence
After each round, check:
- Did Gilfoyle raise new issues? If not → stop.
- Did Dinesh concede everything? If not → continue.
- At round cap → ask user to continue or wrap up.
Step 4: Final Summary
## Dinesh vs Gilfoyle Review — [target]
### [N] rounds
### Best of the Banter
[2-4 funniest exchanges]
### Verdict
#### Critical (Gilfoyle won, Dinesh conceded)
- `file:line` — issue — fix
#### Important (Gilfoyle won after debate)
- `file:line` — issue — fix
#### Contested (Dinesh held his ground)
- `file:line` — what was raised — why defense holds
#### Dismissed (Nitpicks)
- `file:line` — why it doesn't matter
### Strengths
[What even Gilfoyle grudgingly acknowledged]
### Recommended Changes
- [ ] `file:line` — what to change
- [ ] `file:line` — what to change
If nothing to fix: "Nothing to fix. Gilfoyle is furious."
### Score
Gilfoyle: X | Dinesh: Y
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.
- 8d ago First seen · 106 lines · 38 tokens per session scan A 6292a35b14c9
dg is a cursor rule published in the GitHub repository v1r3n/dinesh-gilfoyle (191 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,297 once invoked, about $0.0002 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
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
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.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.