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/andr-ca/agentharness/code-review-dbgit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00046 | $0.00925 |
| Opus 5 | $0.00023 | $0.00463 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
code-review-db 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — Database & Persistence Layer
Focus on performance, correctness, and safety at the data layer.
Query Correctness
- N+1 queries — a loop that loads related records per item. Look for
for item in items: item.related. Fix with eager loading (select_related,include,JOIN) or a batch fetch outside the loop. - Unbounded queries —
find_all(),SELECT *with noLIMIT,WHERE 1=1. Every read from a growing table needs pagination or aLIMIT. - Missing WHERE clause — an
UPDATEorDELETEwith no filter deletes/updates every row. - Implicit full-table scan — a
WHEREon a column with no index. CheckEXPLAINoutput or migration history. - Fetching more columns than needed —
SELECT *when only 2 columns are used. Unnecessary data transfer and harder to cache.
Index Strategy
- Missing index on foreign key —
FKcolumns not in an index cause full scans on JOIN and cascade operations. - Missing index on
WHERE/ORDER BYcolumns — any column used in a filter, sort, or join should have an index unless the table is tiny (<1k rows). - Index on every column — over-indexing slows writes. Indexes serve reads; add them only for proven query patterns.
- Composite index column order — a composite index on (A, B, C) helps queries filtering A, or A+B, but NOT B alone. Confirm the index covers the actual query.
- Index on high-cardinality boolean — a boolean column index is almost never useful (50/50 selectivity).
Transactions & Consistency
- Two writes without a transaction — if the second write fails, the first is orphaned. Wrap in a transaction.
- Transaction too wide — a transaction that spans an HTTP call, a file system operation, or a sleep holds locks and causes contention. Keep transactions as short as possible.
- Read-your-own-writes — reading back a record inside a write transaction without using the same transaction/session. Causes stale reads in read-replica setups.
- Lost update — two concurrent reads followed by two concurrent writes without optimistic or pessimistic locking.
- Missing rollback on error — exception handling that logs and continues without rolling back a partially-committed transaction.
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.
- yesterday First seen · 52 lines · 46 tokens per session scan A f6174050ff15
code-review-db is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 925 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 2026-08-31.
Other cursor rules, from other repositories
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.