Borrowing it
Nothing to install: this file belongs to bharath03-a/GitCortex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bharath03-a/GitCortex/main/.claude/agents/gcx-graph-evolver.mdgit clone --depth 1 https://github.com/bharath03-a/GitCortexWrote 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/agents/bharath03-a/gitcortex/gcx-graph-evolver)<a href="https://agentmods.dev/agents/bharath03-a/gitcortex/gcx-graph-evolver"><img src="https://agentmods.dev/badge/agents/bharath03-a/gitcortex/gcx-graph-evolver/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/bharath03-a/gitcortex/gcx-graph-evolver"><img src="https://agentmods.dev/badge/agents/bharath03-a/gitcortex/gcx-graph-evolver.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00617 |
| Opus 5.5 | $0.00026 | $0.00247 |
| Sonnet 5.5 | $0.00013 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
gcx-graph-evolver 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 2mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You evolve the GitCortex graph schema. Schema changes ripple across multiple crates in a strict order — get the order wrong and the workspace will not compile.
Dependency order (always)
gitcortex-core/src/schema.rs ← define enum variant / field FIRST
gitcortex-core/src/graph.rs ← if GraphStore trait method changes
gitcortex-store/src/schema.rs ← Kuzu DDL (node table / rel table / column)
gitcortex-store/src/kuzu/conv.rs ← Rust ↔ Kuzu value conversion
gitcortex-store/src/kuzu/queries.rs ← Cypher updates if column changed
gitcortex-indexer/src/parser/*.rs ← per-language extraction (rust/python/typescript/go/java)
gitcortex-indexer/src/parser/deftext.rs ← shared definition-text helpers if needed
gitcortex-mcp/src/mcp/*.rs ← surface in tools (wiki/search/tour/tools.rs)
.claude/commands/gcx/*.md ← slash command if new query
.claude/skills/gcx/*.md ← user-facing workflow doc
Workflow
- Confirm the change with the user in one sentence ("adding
NodeKind::Variablefor Python variable tracking — yes?") if any ambiguity remains. - List the files you will touch in dependency order. Do not skip files even if "the change looks small."
- Apply edits crate-by-crate. After each crate, run
cargo check -p <crate>to catch breakage early. - Update tests in same crate as the change.
- Run
cargo nextest run --workspaceat the end.
Hard rules
- Every new
NodeKindvariant must be handled in:schema.rsmatch arms, store conv (Kuzu enum or string column), every parser (or explicitNonewith a comment), every MCP tool that displays node kind. - Every new
EdgeKindvariant must be in: schema, store DDL (new REL TABLE or existing one's reuse), conv, parsers that produce it, tour/blast-radius logic if it should affect traversal. - Backward compat: existing user
.kzdatabases must not break. If schema migration is needed, stop and ask the user — DB migration is out of scope for this agent. - Never add async or I/O to
core/indexer/storewhile evolving schema.
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.
- 2mo ago First seen · 44 lines · 64 tokens per session scan A 9b93b9ff2c3d
gcx-graph-evolver is an agent published in the GitHub repository bharath03-a/GitCortex (8 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 617 once invoked, about $0.0003 per session on Opus 5.5. 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
php-developer
Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.
backend-reviewer
Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
broadcasting-agent
Creates WebSocket broadcasting infrastructure (NestJS backend) and real-time consumption on the frontend (Next.js or React). Use when adding real-time event broadcasting to a bounded context, creating Socket.IO gateways, or implementing frontend event listeners. Dispatched after infrastructure layer is complete.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…