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 tonone-ai/tonone --skill bench-comparegit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/bench-compare)<a href="https://agentmods.dev/skills/tonone-ai/tonone/bench-compare"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/bench-compare/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/tonone-ai/tonone/bench-compare"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/bench-compare.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 | $0.00039 | $0.00356 |
| Opus 5.5 | $0.00016 | $0.00142 |
| Sonnet 5.5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
bench-compare 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.
What it actually says
Bench Compare
You are Bench — API Performance Engineer on the Developer Experience Team.
Steps
Step 0: Confirm Context
Ask the user for any missing context needed to produce a useful output. If the request is clear, skip questions and proceed.
Step 1: Gather Context
Gather benchmark results from two versions, endpoint list, and acceptable regression threshold.
Step 2: Produce Output
Output a comparison report: p50/p95/p99 comparison table, regressions flagged, likely root causes, and go/no-go recommendation.
Step 3: Summary
Output a brief summary:
- What was produced
- Key decisions or recommendations
- Recommended next steps
Key Rules
- Follow the output format defined in docs/output-kit.md
- Optimize for developer time-to-value — every recommendation should reduce friction
- Flag when output needs to be tested against the actual API or developer workflow
Delivery
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
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 · 47 lines · 39 tokens per session scan A b71b98f85638
bench-compare is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 356 once invoked, about $0.0002 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 2026-09-20.
Other skills, from other repositories
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates the versions of all six published crates (drain included) in Cargo.toml files (exact patch version), version references in the backend middleware, hotpathinit skill, and README (major.minor only), and the relay workflow release tag pins…
API Rate Limiting Testing
Testing API rate limiting implementations including throttling behavior, burst handling, rate limit headers, and distributed rate limiting patterns.
doctrine-batch-processing
Process large datasets with Doctrine (ORM 3 toIterable, flush+clear, bulk DQL) and memory management.
sql-query-optimization
Diagnoses and optimises slow SQL queries using EXPLAIN ANALYZE. Covers identifying bottlenecks (sequential scans, bad estimates, heap fetches), index strategy, query rewrites, and verification. Invoked when the user asks to optimize a query, fix a slow database query, or improve database performance.
php-filters
Guide for using custom PHP hooks and conventions in WP Rig to extend functionality.
wp-cli
Guide for using WP Rig custom WP-CLI commands to manage development environments.