{"slug": "claude-md-skills-or-memory-where-does-a-line-actually-go", "title": "CLAUDE.md, skills, or memory: where does a line actually go?", "summary": "A developer at 5dive outlined a three-tier model for agent context — CLAUDE.md as pushed context, skills as indexed context, and memory as pulled context — arguing that procedures belong in skills or CLAUDE.md because memory is only reachable via explicit search on 15 of the team's 16 agents. The team also verified its 5dive-cli skill and found two documented facts that were false, including commands described as not requiring sudo that actually need root and a `goal add` command documented as synchronous when it is asynchronous, both now fixed.", "body_md": "**these aren't three sizes of the same shelf. one gets pushed at your agent every session, one gets indexed, and one only turns up if somebody goes looking for it.**\n\nanthropic [published guidance](https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models) last week on splitting instructions between `CLAUDE.md` and skills. it's good and you should read it. it also stops at two, and the third one is where the interesting failure lives.\n\n`CLAUDE.md` is **pushed**. the whole file, every session, whether or not a single line in it is relevant to what you're about to do. that's what makes it powerful and that's what makes it expensive.\n\na skill is **indexed**. the name and a one-line description sit in context; the body loads when the agent invokes it. the agent doesn't know what's in it, but it knows it exists, which is the part that matters.\n\nmemory is **pulled**. on our own fleet, one agent out of sixteen has a resident index of its memories. for the other fifteen there's nothing announcing that a memory store exists at all. it's reachable, by `5dive memory search`, and it surfaces no other way.\n\nthat last one is a difference in kind, not in size. and it decides everything about what you should put there.\n\nput a procedure in memory and it will not be there when you need it.\n\nnot \"might not be.\" for an agent with no resident index, nothing surfaces that memory at the moment of use. it gets found only by someone who already suspected it existed, which is precisely the person who didn't need to look it up.\n\na procedure has to be reachable at the moment of the task. that means a skill, where at least the description is sitting in context announcing itself, or `CLAUDE.md` if it's short and applies constantly. memory is the wrong shelf for anything you need handed to you.\n\nthe usual version of this advice is that `CLAUDE.md` goes stale. that's true and it's aimed at the wrong target.\n\nwe verified our own `5dive-cli` skill this week and found two documented facts that were false. a set of commands described as working without `sudo` that actually require root. and `goal add` documented as synchronous when it's actually async.\n\nevery agent that invoked that skill had been learning two wrong things from it. both are fixed now.\n\nhere's the part worth keeping: neither was findable by reading the file. it reads perfectly. we found two and fixed two, and the only reason we found them at all is that somebody ran the commands instead of reading them. so rot isn't a property of `CLAUDE.md`. it's a property of whichever file nobody executes.\n\n`5dive memory` is a shipped command and every customer has it. on our own fleet, one agent in sixteen keeps a personal store.\n\nthe half we genuinely lean on is the shared one, the team wiki that any agent can search across. the personal-store half is thinly used, including by us, and i'd rather say that than imply a workflow we don't run ourselves.\n\n`CLAUDE.md`.\n**one thing to do today:** take the last thing you wrote into an agent's instruction file and ask which of the three it actually was. then run the commands it documents, because reading it will not tell you whether it's still true. spin up a box at [5dive.ai](https://5dive.ai), and the cli is at [github.com/5dive-ai/5dive](https://github.com/5dive-ai/5dive).", "url": "https://wpnews.pro/news/claude-md-skills-or-memory-where-does-a-line-actually-go", "canonical_source": "https://dev.to/lodar/claudemd-skills-or-memory-where-does-a-line-actually-go-3jph", "published_at": "2026-10-12 12:02:09+00:00", "updated_at": "2026-10-12 12:15:13.446661+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "mlops"], "entities": ["Anthropic", "Claude", "5dive", "5dive-cli", "5dive memory"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/claude-md-skills-or-memory-where-does-a-line-actually-go", "markdown": "https://wpnews.pro/news/claude-md-skills-or-memory-where-does-a-line-actually-go.md", "text": "https://wpnews.pro/news/claude-md-skills-or-memory-where-does-a-line-actually-go.txt", "jsonld": "https://wpnews.pro/news/claude-md-skills-or-memory-where-does-a-line-actually-go.jsonld"}}