YDMmobile / oss
KOEN

Keyword / 23 entries

ai

Writing with this keyword. All writing

Category
  1. 1

    One Repo, Two Agents, No ~/.claude: 5 Rules for Making Claude Code and Codex Behave the Same

    What I found when I tried to make a repository carry its own agent rules for both runtimes My agents are well trained, as long as they run on my Mac. On 2026-10-01 my ~/.claude held a 22,449-byte CLAUDE.md, 12 rule files, 7 agents, hooks on five events and 24 enabled plugins. My ~/.codex held a 31,128-byte AGENTS.md,…

    EN2026-10-22

  2. 2

    Your Global Claude Code Skills Shouldn't Know Your Framework

    They should know how to ask your repo — five times mine knew too much On 2026-06-12 I rewrote three skills in my global Claude Code folder, because one of my own projects was living inside them. Not a reference to it. The project itself. My semantic-commit skill, which I had added on 2026-04-19, told the agent to…

    EN2026-10-22

  3. 3

    I Vendored Two Third-Party Claude Code Skills. A 49-Day Census Found Zero Calls.

    A counter-list to the "plugins every developer should install" posts: five things my own transcripts taught me My feed keeps serving me lists of Claude Code plugins and skills I apparently cannot live without. I read them. I also install things: at my 2026-09-03 census, my global skills folder held 36 user skills. So…

    EN2026-10-21

  4. 4

    4 Things Claude Code Subagents Don't Inherit (and 1 Thing They Do)

    What I learned when my own subagents ignored my rules, skipped my gates, refused my approval, and read my answer key On 2026-10-02 I was testing a new Claude Code skill by running it through subagent scenarios. One of the subagents did exactly what the skill told it to do: it stopped at the plan-approval gate, showed…

    EN2026-10-20

  5. 5

    Your Claude Code Skills Are Invisible Past 1% of Context: 5 Checks Before You Rewrite a Description

    A skill that never fires may not have a weak description. It may have no description at all. You write a skill. You give it a careful description. Then you wait for Claude to reach for it, and it never does. The natural next step is to rewrite the description: make it sharper, add trigger words, maybe add an…

    EN2026-10-19

  6. 6

    My CLAUDE.md Is a Router, Not a Manual: 6 Rules From Three of My Repos

    Almost every line should send the agent to another file. These are the places where mine did not, and what went stale. On the morning of 2026-03-23, I made the CLAUDE.md in mirae, my Flutter alarm app, as helpful as I could. It had the package structure, the flavors, the Riverpod codegen rules, a TDD protocol, a "What…

    EN2026-10-18

  7. 7

    Chef Watson Already Gave Me Ideas. What Does Epicure Add?

    I used to be a chef. That probably explains why a video about ingredient embeddings managed to interrupt my scrolling so efficiently. The paper was Epicure, and the question it brought back was older than the paper: how useful has AI actually become in a kitchen? I had used IBM's Chef Watson around 2015, when AI was…

    EN2026-10-17

  8. 8

    Anthropic's Scion: What Happens When Writing Code Outruns Moving It?

    Imagine asking an agent for a small change, then watching the job spend longer preparing its workspace than doing useful work. Now imagine launching more agents to make things faster. (The checkout step would like a word.) That hypothetical is my starting question for Scion: what are we paying to prepare each unit of…

    EN2026-10-16

  9. 9

    AI Can Write the Commit Subject. It Cannot Approve the Commit.

    A good commit message is small, which is why it is so easy to postpone until the exact moment your brain is tired of the diff. AI can summarize that diff. The dangerous part is everything around the summary: which files are sent, whether unstaged work gets mixed in, whether a lockfile consumes the entire context,…

    EN2026-10-15

  10. 10

    Codex Can Generate Images. I Wanted a Contact Sheet.

    Generating one image with Codex is fine. Generating five candidates, comparing them, finding the prompt that produced the good one, attaching a reference, re-rolling, and saving the winner is where the workflow starts shedding parts. The image tool runs inside an agent turn. There is no standalone imagegen command to…

    EN2026-10-12

  11. 11

    When AI Joins the Pull Request, Review Depth Still Comes From Risk

    One wiki pull request received 13 findings in its first hosted review round. The fixes landed, and the local review drain became clean. The next hosted round found seven more defects. All seven had been introduced by the first fixes, and six were contradictions with nearby sentences on the same pages. Later rounds…

    EN2026-10-02

  12. 12

    Replace Agent Adjectives With Verifiable Verbs

    “Be careful” may be the least testable instruction in a coding repository. It sounds responsible. So do “make a high-quality change,” “be thorough,” and “use good judgment.” These phrases give an instruction file a reassuring tone and give the agent almost no observable boundary. When the result was wrong, the only…

    EN2026-09-27