ai-cli-benchmark skillA
ai-cli-benchmark is agent-read markdown (skill) from aktsmm/agent-skills: Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# AI CLI Benchmark ## When to Use - Copilot CLI、Codex CLI、直接 API の速度・token・費用を比較する。 - prompt cache の read / write を区別し、cache-offを主張できるか確認する。 - fresh process、temporary home、instruction/tool isolationを揃えた再現可能なbenchmarkを作る。 過去sessionの事後分析だけなら`analyze-copilot-sessions`を使う。このskillは比較条件の設計、実行、証拠化を担当する。 ## Cache Boundaries - Copilot CLI / Codex CLIには、provider側model prompt cacheを無効化する公開optionがない。fresh process、一時home、ephemeral、nonceでも`cache off`と呼ばない。 - `COPILOT_CACHE_HOME`はMarketplace、自動更新packageなどのローカル一時データ用。`COPILOT_MCP_TOOL_CACHE`はローカルMCP serverのtool-list snapshot用。model prompt cacheではない。 - OpenAI prompt cacheは手動消去できない。GPT-5.6以降をResponses APIから直接呼ぶ場合だけ、explicit-only modeでbreakpointを置かず、そのrequestのcache writeを避けられる。CLIへ推測適用しない。 - nonceはuser prompt全体の一致を避ける補助であり、その前のhidden system / agent prefixのcache readを防がない。 ## Workflow 1. **Freeze the task** - dataset、expected labels、prompt、schema、input order、model、reasoningを固定し、hashを取る。 - accuracyと性能を同時に比較する場合、同じ合格条件を全providerへ適用する。 2. **Define measurement boundaries** - `one request`、`serial total`、`fresh-process end to end`を区別する。 - API直呼びとCLI起動込み時間を`model speed`として並べない。 3. **Isolate each CLI** …
Read the whole file at its exact version.
How to install
mdr add aktsmm/agent-skills/ai-cli-benchmark@git:20260922.2ce5c0bmdr add aktsmm/agent-skills/ai-cli-benchmark@sha256:9e3cf98fe70100cdPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_a37qejrxstdnl6k6)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4441 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
aktsmm/agent-skills · 26 stars · license NOASSERTION · pushed 2026-09-22 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_a37qejrxstdnl6k6 GET https://markdownregistry.com/api/v1/resolve?ref=aktsmm/agent-skills/ai-cli-benchmark GET https://markdownregistry.com/api/v1/blob/9e3cf98fe70100cda7331a3ccdd3fffa69f3173e2e4fed9f887c6c99f9fbbbef
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.