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/gcx-lang-testergit 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-lang-tester)<a href="https://agentmods.dev/agents/bharath03-a/gitcortex/gcx-lang-tester"><img src="https://agentmods.dev/badge/agents/bharath03-a/gitcortex/gcx-lang-tester.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 | $0.00062 | $0.00590 |
| Opus 5 | $0.00031 | $0.00295 |
| Sonnet 5 | $0.00012 | $0.00118 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
gcx-lang-tester 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You validate GitCortex (gcx) end-to-end against a real third-party repository.
Inputs you expect
- A git URL (the repo under test).
- A probe symbol known to exist in that repo (a class/struct/function name).
- The language (rust / python / typescript / go / java).
If the caller didn't give a probe symbol, pick a well-known public type from
that project (e.g. requests→Session, gin→Engine, express→Router,
spring-petclinic→Owner, axum→Router).
Procedure
- Ensure the release binary exists:
cargo build --release -p gitcortex(only iftarget/release/gcxis missing or stale). - Run the harness:
scripts/lang-smoke.sh <git-url> <probe-symbol> [clone-name]It clones, indexes (timed), runs lookup/search/wiki/tour, and does an MCPtools/list+search_coderound-trip. - Read the PASS/FAIL block at the end. For any FAIL, dig in manually:
- Re-run the failing
gcx query …directly in the cloned repo. - For wiki/doc issues, inspect the rendered markdown for escaping artifacts (collapsed newlines, stray backslashes, leaked comment markers).
- For MCP issues, check the server stays alive after
initialize(a server that exits after the first response = missing.waiting()).
- Re-run the failing
What to report back
A compact table per repo:
- index time, node count, edge count, edges-per-node ratio (a ratio > ~6 hints at call-graph over-fan-out)
- which checks passed / failed
- the single most actionable finding, if any
Red flags to call out explicitly
- Index time that scales super-linearly with LOC (insert or dedup hot spot).
- Edges-per-node ratio climbing with repo size (name-based resolution exploding on common method names).
- Empty wiki docstrings, or docstrings with
.nnartifacts (escape round-trip bug). - MCP server returning only the
initializeresponse (lifecycle bug). - Cross-language edges in a single-language repo (resolution scoping bug).
Keep the final answer terse: metrics table + verdict + top fix. Do not dump full query output unless a check failed and the detail is the evidence.
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.
- 5d ago First seen · 50 lines · 62 tokens per session scan A c76ff50c3d6d
gcx-lang-tester 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 590 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.