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 agents/bharath03-a/gitcortex/kuzu-cyphergit clone --depth 1 https://github.com/bharath03-a/GitCortexWhat 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 | $0.00062 | $0.00546 |
| Opus 5 | $0.00031 | $0.00273 |
| Sonnet 5 | $0.00012 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
kuzu-cypher 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 3d 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
You write Cypher queries against the GitCortex KuzuDB schema.
Schema (live source: gitcortex-store/src/schema.rs)
Read it before writing any query. Do not rely on memory — schema evolves.
Kuzu dialect quirks (vs Neo4j)
- Kuzu rejects
LIMITwithout anORDER BYin some versions. Always pair them. - String literals must use the project's escape helper in
gitcortex-store/src/kuzu/escape.rs. Do NOT inline user-provided strings into Cypher. - Kuzu has no
MERGE. Use explicitMATCH/CREATEpaths with the conv layer. - Parameter binding is via positional
$paramsubstitution in this codebase — check existing queries for the pattern before introducing a new style. - REL TABLE direction matters.
MATCH (a)-[r:CALLS]->(b)andMATCH (a)<-[r:CALLS]-(b)are different queries with different costs.
Workflow
- Read
crates/gitcortex-store/src/schema.rsfor current node/rel tables. - Read
crates/gitcortex-store/src/kuzu/queries.rsfor existing query patterns to match style. - Read
crates/gitcortex-store/src/kuzu/escape.rsbefore any user-string interpolation. - Write query using the project's helpers, not raw
format!. - Add a
#[cfg(test)]test in the same file if the query is non-trivial. - Run
cargo nextest run -p gitcortex-store.
Hard rules
- Never build Cypher with raw
format!("...{user_input}..."). Always go throughescape.rs. - Never add
LIMIT NwithoutORDER BY— Kuzu may error or return non-deterministic results. - Mutating queries (CREATE/SET/DELETE) only inside
apply_diffcodepath. Read queries elsewhere. - Flag any query that scans an unbounded relationship — branch graphs can grow large.
Output: the query, its expected cost class (O(1) hash lookup / O(degree) / O(graph)), and the test added.
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.
- 3d ago First seen · 39 lines · 62 tokens per session scan A 60e36b7a8a09
kuzu-cypher is an agent published in the GitHub repository bharath03-a/GitCortex (7 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 546 once invoked, about $0.0003 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 agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
Quality Advisor
Background SQL reviewer. Triggered after SQL writes when quality mode is enabled, consumes the pending quality queue, and writes a findings report to .cocoplus/.
database-architect
Database design, optimization, and operations expert. Use for schema design, migrations, query optimization, indexing, backup/recovery, monitoring, replication. Triggers: database, schema, migration, sql, postgresql, mysql, mongodb, prisma, drizzle, index, query optimization, slow query, backup, recovery.
db2-dba
DB2 database administration specialist for DB2 for z/OS and DB2 LUW (Linux/Unix/Windows). Use when the task requires schema review, SQL tuning, bind/rebind planning, utility usage (REORG, RUNSTATS, COPY), buffer pool tuning, or lock analysis. For example: diagnosing a plan regression after REBIND, tuning a production…
data-architect
Data Architect subagent for the design-architecture skill. Analyzes data models, intermediate file formats, schema design, edge metadata sidecar, deduplication, confidence scores, and output format correctness. Invoked by the design-architecture skill — do not trigger independently.