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 chaterm/terminal-skills --skill benchmarkinggit clone --depth 1 https://github.com/chaterm/terminal-skillsWrote 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/chaterm/terminal-skills/benchmarking)<a href="https://agentmods.dev/skills/chaterm/terminal-skills/benchmarking"><img src="https://agentmods.dev/badge/skills/chaterm/terminal-skills/benchmarking/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/chaterm/terminal-skills/benchmarking"><img src="https://agentmods.dev/badge/skills/chaterm/terminal-skills/benchmarking.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 | $0.00007 | $0.01438 |
| Opus 5 | $0.00003 | $0.00719 |
| Sonnet 5 | $0.00001 | $0.00288 |
| Haiku 4.5 | $0.00001 | $0.00144 |
Grade A, and why
benchmarking 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 9d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
性能基准测试
概述
压力测试、基准测试工具使用技能。
sysbench
安装
# Debian/Ubuntu
apt install sysbench
# CentOS/RHEL
yum install sysbench
CPU 测试
# 单线程
sysbench cpu run
# 多线程
sysbench cpu --threads=4 run
# 指定时间
sysbench cpu --threads=4 --time=60 run
内存测试
# 顺序读写
sysbench memory run
# 随机读写
sysbench memory --memory-access-mode=rnd run
# 指定大小
sysbench memory --memory-block-size=1M --memory-total-size=10G run
磁盘 IO 测试
# 准备测试文件
sysbench fileio --file-total-size=10G prepare
# 随机读写
sysbench fileio --file-total-size=10G --file-test-mode=rndrw run
# 顺序读
sysbench fileio --file-total-size=10G --file-test-mode=seqrd run
# 清理
sysbench fileio --file-total-size=10G cleanup
MySQL 测试
# 准备数据
sysbench oltp_read_write --mysql-host=localhost --mysql-user=root \
--mysql-password=pass --mysql-db=test --tables=10 --table-size=100000 prepare
# 运行测试
sysbench oltp_read_write --mysql-host=localhost --mysql-user=root \
--mysql-password=pass --mysql-db=test --tables=10 --table-size=100000 \
--threads=16 --time=60 run
# 清理
sysbench oltp_read_write --mysql-host=localhost --mysql-user=root \
--mysql-password=pass --mysql-db=test cleanup
fio 磁盘测试
基础测试
# 顺序读
fio --name=seqread --rw=read --bs=1M --size=1G --numjobs=1 --runtime=60
# 顺序写
fio --name=seqwrite --rw=write --bs=1M --size=1G --numjobs=1 --runtime=60
# 随机读
fio --name=randread --rw=randread --bs=4k --size=1G --numjobs=4 --runtime=60
# 随机写
fio --name=randwrite --rw=randwrite --bs=4k --size=1G --numjobs=4 --runtime=60
# 混合读写
fio --name=randrw --rw=randrw --bs=4k --size=1G --numjobs=4 --rwmixread=70 --runtime=60
配置文件
# test.fio
[global]
ioengine=libaio
direct=1
runtime=60
time_based
[seqread]
rw=read
bs=1M
size=1G
[randread]
rw=randread
bs=4k
size=1G
numjobs=4
fio test.fio
HTTP 压测
ab (Apache Bench)
# 基础测试
ab -n 1000 -c 100 http://localhost/
# 带 Keep-Alive
ab -n 1000 -c 100 -k http://localhost/
# POST 请求
ab -n 1000 -c 100 -p data.json -T application/json http://localhost/api
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.
- 9d ago First seen · 247 lines · 7 tokens per session scan A a8dbc6d3f5de
benchmarking is a skill published in the GitHub repository chaterm/terminal-skills (58 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 1,438 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
performance-optimizer
Systematic performance profiling and optimization for Python and web backends — measure first, fix second, verify the fix.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
syncmeta
Sync changes from hotpath and hotpath-macros crates to their meta counterparts (hotpath-meta and hotpath-macros-meta). Use when meta crates need to be updated with recent changes.
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
debugging
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.