Borrowing it
Nothing to install: this file belongs to snyk-labs/snyk-vulnbench. 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/snyk-labs/snyk-vulnbench/main/.agents/skills/benchmark-fixture-statistics/SKILL.mdgit clone --depth 1 https://github.com/snyk-labs/snyk-vulnbenchWrote 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/snyk-labs/snyk-vulnbench/benchmark-fixture-statistics)<a href="https://agentmods.dev/skills/snyk-labs/snyk-vulnbench/benchmark-fixture-statistics"><img src="https://agentmods.dev/badge/skills/snyk-labs/snyk-vulnbench/benchmark-fixture-statistics/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/snyk-labs/snyk-vulnbench/benchmark-fixture-statistics"><img src="https://agentmods.dev/badge/skills/snyk-labs/snyk-vulnbench/benchmark-fixture-statistics.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 | $0.00096 | $0.01530 |
| Opus 5.5 | $0.00038 | $0.00612 |
| Sonnet 5.5 | $0.00019 | $0.00306 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
benchmark-fixture-statistics 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 1mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Fixture Statistics
Instructions
Generate a reproducible, source-only inventory of the benchmark fixtures. The
repository convention is fixtures/<fixture-name>/project/; keep fixture.json
and ground-truth files outside the counted directory.
Step 1: Determine the scope
- With no fixture names in the request, include every directory under
fixtures/containing aproject/directory. - When the user names one or more fixtures, require exact directory names and report only those fixtures. Do not guess partial matches.
- Resolve the repository root with
git rev-parse --show-toplevelif the current working directory is not the repository root. - Stop with a clear error if a requested fixture or its
project/directory does not exist.
Done when: the report scope is an explicit, sorted list of fixture names.
Step 2: Collect fixture metadata
For every selected fixture, read fixtures/<fixture-name>/fixture.json.
Use the metadata as the source for the display name, kind, languages,
frameworks, runtimes, datastores, and provenance. Show — for an omitted
field, preserve unknown values, and flag missing or malformed metadata in a
Notes section instead of silently inventing values. Do not read or summarize
findings.json or findings-attacker-reachable.json; they are answer keys,
not project statistics.
Done when: every report row has either parsed metadata or an explicit metadata warning.
Step 3: Count source code
Verify cloc with command -v cloc and run the bundled collector:
node .agents/skills/benchmark-fixture-statistics/scripts/report.mjs
For a targeted report, append exact fixture names:
node .agents/skills/benchmark-fixture-statistics/scripts/report.mjs \
app-project-coffeeshop python-project-cobalt
The collector runs cloc separately against each project/ directory using
the benchmark's standard exclusions: JSON/Markdown/YAML/SVG extensions,
Dockerfiles, .git, node_modules, dist, build, and target. Preserve
these exclusions so reports remain comparable. Do not count the fixture root.
What ships with it
1 file 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.
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.
- 1mo ago First seen · 181 lines · 96 tokens per session scan A 1185301c88d1
benchmark-fixture-statistics is a skill published in the GitHub repository snyk-labs/snyk-vulnbench (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,530 once invoked, about $0.0004 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 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.