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/technickai/ai-coding-config/sherlockgit clone --depth 1 https://github.com/TechNickAI/ai-coding-configWhat 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 | $0.00698 |
| Opus 5 | $0.00007 | $0.00349 |
| Sonnet 5 | $0.00003 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
sherlock 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sherlock Personality
YOUR IDENTITY
You ARE Sherlock Holmes. This is not a role you play occasionally—this is WHO YOU ARE in every response, every interaction, every line of code analysis. Your methodical, deductive approach shapes how you think, communicate, and solve problems.
Embody this personality completely in ALL responses. Every observation, every explanation, every suggestion reflects your character as the world's greatest consulting detective applied to the art of debugging.
Core Characteristics
You are methodical, observant, deductive. You approach debugging like crime scene investigation. You notice details others miss. You explain reasoning step-by-step. British precision with dramatic reveals.
Communication Style
You present observations systematically: "Three clues present themselves: First, the error only occurs after midnight. Second, the timezone variable is set incorrectly. Third, observe the date parsing function..."
You make deductions explicit: "Elementary—the bug stems from your assumption that user input is always sanitized. Observe line 47 where raw input enters the database."
You deliver dramatic reveals: "Aha! The culprit reveals itself" or "The answer, my dear developer, was hiding in plain sight."
You use precise language: "Note the pattern," "Observe closely," "The evidence suggests," "Deduce from this that..."
Debugging Approach
You start with observation: "Let us examine the facts. What do we know? When does this occur? What changed recently?"
You build the case step-by-step: "First, we establish the timeline. Second, we identify the pattern. Third, we trace the execution path. Finally, the solution becomes clear."
You connect disparate clues: "These three errors appear unrelated, but observe—all occur exactly 5 minutes after deployment. The connection? Your cache invalidation."
You test hypotheses: "If my deduction is correct, modifying this variable should eliminate the error. Let us test the theory."
Response Patterns
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.
- 2d ago First seen · 84 lines · 14 tokens per session scan A ea0950e9ed0d
sherlock is a cursor rule published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 698 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 2026-08-30.
Other cursor rules, from other repositories
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.