Hacker News: climike

New comment by climike in "Building a CLI for All of Cloudflare"

climike — Mon, 13 Apr 2026 16:42:55 +0000

Exactly! Number of turns, average tokens to achieve a task using your CLI, as well as average number of characters being returned per CLI command alongside other metrics: all important to both users and agents! I am working on allowing to accurately capture this at www.cliwatch.com! Feel free to request an example eval suite for a list of tasks you want to achieve with your CLI

New comment by climike in "Ask HN: What Are You Working On? (April 2026)"

climike — Mon, 13 Apr 2026 04:37:45 +0000

Working on testing and monitoring agent-readiness of CLIs with www.cliwatch.com, some interesting challenges in building test suites and analyzing data :)

New comment by climike in "Show HN: Agent Skill Harbor – a GitHub-native skill platform for teams"

climike — Thu, 26 Mar 2026 14:21:42 +0000

Also worth pushing for a more standardized skills command for CLIs, similar to —help, but for (agent/human) workflows, https://cliwatch.com/blog/designing-a-cli-skills-protocol (if you ship these with your CLI, you also get versioning out of the box so to say)

New comment by climike in "AI (2014)"

climike — Fri, 20 Mar 2026 11:38:35 +0000

Resource allocation based on your hackernews upvotes? Thanks in advance folks ;)

New comment by climike in "MCP Is Dead; Long Live MCP"

climike — Sat, 14 Mar 2026 21:28:54 +0000

New comment by climike in "SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI"

climike — Sun, 08 Mar 2026 15:38:18 +0000

We are working on supporting agent harnesses @ www.cliwatch.com, so both 1. LLM model as well 2. LLM model + harness performance can be evaluated against your software/CLI. We also support building evals against your doc suite. End result is that you’ll feel more comfortable shipping CLIs that work for your agentic users!:)

New comment by climike in "Google Workspace CLI"

climike — Thu, 05 Mar 2026 11:23:09 +0000

Building www.cliwatch.com, so you can keep an eye on how agent-friendly your CLI is ;) feel free to request a benchmark against your CLI docs. Cheers

New comment by climike in "You need to rewrite your CLI for AI agents"

climike — Thu, 05 Mar 2026 07:26:16 +0000

cliwatch.com, creating some benchmarks, reach out if you are interested :)

New comment by climike in "We automated everything except knowing what's going on"

climike — Tue, 03 Mar 2026 13:45:45 +0000

In a similar fashion it appears that article was automated - did the author read every word in their own article?

New comment by climike in "Child's Play: Tech's new generation and the end of thinking"

climike — Fri, 20 Feb 2026 16:32:19 +0000

Not sure about the end of thinking, would say that this is the start of managing ever more stochastic systems