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/ashlesh-t/cognirepo/cursor_rulesgit clone --depth 1 https://github.com/ashlesh-t/cognirepoWrote 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/ashlesh-t/cognirepo/cursor_rules)<a href="https://agentmods.dev/rules/ashlesh-t/cognirepo/cursor_rules"><img src="https://agentmods.dev/badge/rules/ashlesh-t/cognirepo/cursor_rules.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 | $0.00212 | $0.00212 |
| Opus 5 | $0.00106 | $0.00106 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
cursor_rules 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.
What it actually says
CogniRepo Tool Routing
Project: {project_name} Data: {project_path}/.cognirepo/
BEFORE reading any file >100 lines: use mcp_{project_name}context_pack first. BEFORE searching for a function: use mcp{project_name}lookup_symbol first. BEFORE tracing callers: use mcp{project_name}who_calls first. AFTER a non-trivial decision: use mcp{project_name}_store_memory to record it.
If context_pack returns no_confident_match → fall back to file read. If who_calls returns empty → the fallback field will contain string-literal hits.
For file-specific context (Cursor file mode): use context_pack(file="path/to/file.py") to get all indexed symbols for a file.
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 · 22 lines · 212 tokens per session scan A 94af9ff9aad6
cursor_rules is a cursor rule published in the GitHub repository ashlesh-t/cognirepo (14 stars, last pushed today), licensed MIT. It adds 212 tokens to every session, about $0.0011 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
versioning
Guidelines for library versioning.
codegenome-knowledge-graph
CodeGenome knowledge graph and MCP Context.
php-types-validation
Guidelines for type definitions and validation in PHP MCP SDK.
php-client-implementation
Guidelines for implementing MCP clients in PHP.
php-server-implementation
Guidelines for implementing MCP servers in PHP.
php-mcp-sdk-main
This is the PHP implementation of the Model Context Protocol (MCP) SDK, following the patterns established by the TypeScript SDK.