Borrowing it
Nothing to install: this file belongs to onixhdz/cartograph. 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/onixhdz/cartograph/main/.agents/skills/benchmark-test/SKILL.mdgit clone --depth 1 https://github.com/onixhdz/cartographWrote 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/skills/onixhdz/cartograph/benchmark-test)<a href="https://agentmods.dev/skills/onixhdz/cartograph/benchmark-test"><img src="https://agentmods.dev/badge/skills/onixhdz/cartograph/benchmark-test/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/skills/onixhdz/cartograph/benchmark-test"><img src="https://agentmods.dev/badge/skills/onixhdz/cartograph/benchmark-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 238 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 282 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 286 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00032 | $0.05269 |
| Opus 5.5 | $0.00013 | $0.02108 |
| Sonnet 5.5 | $0.00006 | $0.01054 |
| Haiku 4.5 | $0.00003 | $0.00527 |
Grade A, and why
benchmark-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 549 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cartograph Search Quality Benchmark
Systematic evaluation framework for measuring and improving Cartograph's search quality across keyword and intent queries. Used to validate changes to the embedding pipeline (textgen.go), hybrid search (backend.go), and ingestion (entry_point_scoring.go) without regression.
Quick Start — Run All Batteries
# Prerequisites: dev binary built, server running
task build:dev
./cartograph-darwin-arm64 serve start --no-detach --no-idle &
# 1. Index all test repos (clean + re-embed)
for repo in turbot/steampipe excalidraw/excalidraw fastapi/fastapi hashicorp/nomad gatling/gatling; do
./cartograph-darwin-arm64 clean "$repo"
./cartograph-darwin-arm64 analyze "$repo" --embed=sync
done
# 2. Run batteries (see "Running a Battery" below for per-repo commands)
# 3. Score with score.py (see "Scoring" below)
Architecture of the Benchmark
Battery Files
Each test project has a battery file in batteries/ defining 5 investigations
with keyword + intent query pairs and ground-truth expected symbols:
| File | Language | Nodes | Limit | Investigations |
|---|---|---|---|---|
batteries/steampipe.md |
Go | 882 | 8 | query exec, plugins, db lifecycle, connections, console |
batteries/excalidraw.md |
TypeScript | 1253 | 8 | rendering, export, undo/redo, collaboration, elements |
batteries/fastapi.md |
Python | 756 | 8 | routing, DI, validation, middleware, OpenAPI |
batteries/nomad.md |
Go | 37587 | 15 | startup, scheduling, node failure, raft, client-server |
batteries/gatling.md |
Scala | 11863 | 10 | simulation exec, HTTP protocol, session/stats, actions, assertions |
batteries/gatling-usecases.md |
Scala | 11863 | 10 | redirects, throttling, CSV feeding, reporting, WebSocket, session state |
batteries/mdbook.md |
Rust | 2375 | 8 | CLI dispatch, build pipeline, preprocessors, config/init, serve/watch |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- batteries/dart-frog.md 7.4 KB
- batteries/dart-http.md 6.7 KB
- batteries/dss.md 4.6 KB
- batteries/excalidraw.md 4.7 KB
- batteries/fastapi.md 4.2 KB
- batteries/gatling-usecases.md 6.7 KB
- batteries/gatling.md 7.4 KB
- batteries/mdbook.md 6.4 KB
- batteries/nomad.md 3.8 KB
- batteries/openzeppelin-contracts.md 6.0 KB
- batteries/spring-framework.md 6.2 KB
- batteries/spring-security.md 10 KB
- batteries/steampipe.md 4.7 KB
- batteries/windmill.md 7.1 KB
- score.py 3.5 KB runs code
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 · 549 lines · 32 tokens per session scan A 9d725e9b6d05
benchmark-test is a skill published in the GitHub repository onixhdz/cartograph (14 stars, last pushed 17d ago), licensed MIT. It adds 32 tokens to every session and 5,269 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.