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 skills add jubscodes/get-shit-pretty --skill gspdev-benchmarkgit clone --depth 1 https://github.com/jubscodes/get-shit-prettyWrote 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/jubscodes/get-shit-pretty/gspdev-benchmark)<a href="https://agentmods.dev/skills/jubscodes/get-shit-pretty/gspdev-benchmark"><img src="https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gspdev-benchmark/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/jubscodes/get-shit-pretty/gspdev-benchmark"><img src="https://agentmods.dev/badge/skills/jubscodes/get-shit-pretty/gspdev-benchmark.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 | $0.00026 | $0.00776 |
| Opus 5.5 | $0.00010 | $0.00310 |
| Sonnet 5.5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
gspdev-benchmark 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snapshots live in dev/benchmarks/ as JSON files. The workflow is release-centric:
- At each release, capture a baseline:
benchmark.sh release→{version}.release.json - During development, capture snapshots:
benchmark.sh capture [label] - Before PR, compare against release:
benchmark.sh compare(auto-selects release baseline)
This measures the cumulative impact of changes heading into the next release.
Read $ARGUMENTS to determine the mode:
| Input | Mode |
|---|---|
| (no args) | Capture + auto-compare against release baseline |
capture [label] |
Capture with optional label |
release |
Capture as the release baseline for this version |
compare [v1] [v2] |
Compare two snapshots (default: release vs latest) |
trend |
Show trajectory across all snapshots |
Step 1: Execute mode
Default mode (no args)
- Run
bash dev/scripts/benchmark.sh capture - If a release baseline exists, automatically run
benchmark.sh compare - Present the comparison table and analysis
This is the most common invocation — "where are we vs the last release?"
Capture mode
Run bash dev/scripts/benchmark.sh capture [label].
After capture, read the JSON from dev/benchmarks/ and present a summary:
- Total weight and red-zone count
- Top 5 heaviest skills with their breakdown
- Rate limit risk (API conversations, double-dispatch count)
- If a release baseline exists, auto-compare and highlight changes
Release mode
Run bash dev/scripts/benchmark.sh release.
This is part of the publish flow — capture the definitive baseline for this version. All future compare calls will diff against this baseline until the next release.
Remind the user: "Add benchmark.sh release to your /gspdev-publish checklist."
Compare mode
Run bash dev/scripts/benchmark.sh compare [v1] [v2].
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 · 93 lines · 26 tokens per session scan A 3dd3d918155c
gspdev-benchmark is a skill published in the GitHub repository jubscodes/get-shit-pretty (55 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 776 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
opencli-usage
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
tokf-filter
This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.
gpt-vis
A chart-generation tool that recommends visual formats for data and produces either chart settings or runnable code. It uses GPT-Vis, a library for rendering data visualisations.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.