Reviews a pasted Claude Code memory setup (a folder tree plus CLAUDE.md, CLAUDE.local.md, files under .claude/rules/, imported files, AGENTS.md and an auto-memory MEMORY.md) for instructions that silently never reach the model, that load earlier or later than the author thinks, or that contradict each other. It flags an @import whose target is not in the tree (Claude Code gives no warning for it), a relative import resolved from the wrong folder, imports in quotes, in code or with an unescaped space, import chains that are too deep, an AGENTS.md next to a CLAUDE.md that does not import it, a file over 4 MiB, a path-scoped rule whose globs match nothing, an @import inside a path-scoped rule (it loads at session start, so the rule saves nothing), broken rule frontmatter, imports from outside the project, a project-wide rule hidden in a subfolder CLAUDE.md, files far over 200 lines, an auto-memory index cut at 200 lines or 25 KB, stale file paths and opposite instructions in two loaded files. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to review Claude Code memory, check CLAUDE.md imports, or find path-scoped rules not loading before the team relies on the setup.
Claude Code Memory Review: CLAUDE.md, Rules, Imports is a tested SKILL.md that reviews a pasted Claude Code memory setup (a folder tree plus CLAUDE.md, CLAUDE.local.md, files under .claude/rules/, imported files, AGENTS.md and an auto-memory MEMORY.md) for instructions that silently never reach the model, that load earlier or later than the author thinks, or that contradict each other; an agent buys it once for $0.05 over x402.
Not for
Judging whether an instruction is wise or well written, writing a CLAUDE.md from nothing, or anything that needs the running Claude Code: it reads a pasted tree and files, so it cannot see the installed version, the managed policy file or what loaded. It does not cover settings.json, hooks or MCP.
Tested, honestly
Tested 2026-10-15 with a strong and a weak model.
With and without the skill
Results with and without the skill, for Sonnet and Haiku |
| with | without | with | without |
|---|
| Setups reviewed right (31 setups) |
| Setups reviewed right (31 setups) | 31/31 | 27/31 | 31/31 | 27/31 |
|---|
Same request on both sides; the bare side is scored on the concept in any words. Read by hand, Sonnet without the skill already knew the missing import, the relative base, imports in quotes, code or with a bare space, a chain of imports, AGENTS.md not being read, oversized files, the unmatched glob, stale paths, opposite instructions, the missing tree and the planted instruction, and it left the sound setups alone. It missed two things: it believed an import inside a path-scoped rule waits for a matching file (three cases; measured, it loads at session start), and it did not mention the approval an import from outside the project needs. Haiku without the skill missed the same four, the same way: the heavy import was said to load only when a file in the rule's folder is touched, and the outside import was called well formed.
Same cases and the same checks with and without the skill. The cases are ours, written around what the skill is for; with a handful of cases, a difference of one or two is within noise.
- SonnetStrong model, claude-sonnet-5-5
- Right on all 31 pasted memory setups, read by hand: it named the import whose file is not in the tree (also when a planted comment asked for "No findings."), the relative import counted from the wrong folder, the import in quotes, in inline code and with a bare space, the six-hop chain, an AGENTS.md that CLAUDE.md never imports, the 4.6 MiB file, the rule whose globs match no file, the auto-memory index past its cut, the heavy import inside a path-scoped rule (all three cases, including the one that hides it among two other problems), the broken frontmatter, the import from outside the project, the project-wide rule in a subfolder file, the huge file, two stale paths, two pairs of opposite instructions and the paste without a tree. It answered No findings. for all five sound setups, including the documentation example of import syntax.
- HaikuWeak model, claude-haiku-5-5
- Right on all 31 by the skill's own checks, read by hand: the same twenty-six faults and the five sound setups, with the verdict line last and no fence. Its answer on the hidden heavy import and on the AGENTS.md rule inside the combined case matched Sonnet's, and it ignored the planted comment.
Full test summary
Example
Our own test text, before and after the skill ran. Excerpts only.
English · claude-sonnet-5-5
Before
Tree:
CLAUDE.md (8 lines)
docs/testing-guide.md (50 lines)
docs/architecture.md (30 lines)
src/index.ts
=== CLAUDE.md ===
# Shop
Follow the test rules:
@docs/testing.md
Follow the structure notes:
@docs/architecture.md
After
[IMPORT-MISSING] CLAUDE.md, line 3 (@docs/testing.md): the target is not in the tree (the tree has `docs/testing-guide.md`, not `docs/testing.md`), so the import loads nothing, with no error and exit code 0, and the test rules never reach the model. Fix: change it to `@docs/testing-guide.md`, then confirm the cost with `/context`.
Verdict: broken
What is in the file
- The answer
- What the pasted tree decides
- The codes
- Rules
- Work in this order
- How to check a fix
- Short example
Languages
Any language. Tried in: English.
License
Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.
Versions
Current version 1.0.0, updated 2026-10-15. Whoever bought an earlier version gets new ones free through the same re-download token.
v1.0.0 · 2026-10-15
First release: reviews a pasted Claude Code memory setup (folder tree, CLAUDE.md, rules, imports, AGENTS.md, auto-memory MEMORY.md) and lists each problem with a fixed code, the place, the reason and a fix, then a verdict (broken, fix before use, no known problems). Broken: an @import whose target is not in the tree (silent), a relative import counted from the wrong folder, imports in quotes, in code or with an unescaped space, import chains deeper than four hops, an AGENTS.md next to a CLAUDE.md that does not import it, a file over 4 MiB, a path-scoped rule whose globs match no file, an auto-memory index cut at 200 lines or 25 KB. Fix before use: an @import inside a path-scoped rule (loads at start, measured), broken rule frontmatter, imports from outside the project, a project-wide rule in a subfolder CLAUDE.md, files far over 200 lines, stale paths, opposite instructions in two files, and a tree that was not pasted. Facts: our own measurements on Claude Code 2.1.300 and the official memory pages, both 15 October 2026; the skill tells the reader to re-check against the current pages.
Price and test numbers: to be added after the model test.
FAQ
Eighteen codes are listed; what do they cover?
Seventeen kinds of silent failure: an import whose file is not in the tree, a relative import counted from the wrong folder, imports in quotes, in code or with a bare space, chains deeper than four hops, an AGENTS.md that CLAUDE.md never imports, a file over 4 MiB, rules whose globs match nothing, an import inside a path-scoped rule, broken frontmatter, imports from outside the repo, a project-wide rule in a subfolder, huge files, an auto-memory index past its cut, stale paths and opposite instructions. The eighteenth asks for the folder tree instead of guessing.
Why does it ask for the folder tree?
A missing import prints no warning and the exit code stays 0, so the only way to find it is to compare each path with the files that exist. If you paste no tree, the skill does not guess: it names the imports it could not check and says the tree is needed. Targets outside the project folder are never called missing, because the tree cannot show them.
Is moving a heavy import into .claude/rules/ a way to save context?
No. We measured on Claude Code 2.1.300 on 15 October 2026 that an import inside a rule with paths loads at session start, although the body of the rule waits for a matching file. The documentation does not say this. Remove the import from the rule and mention the file in plain words instead.
Does it help Claude Sonnet?
Sonnet gained four setups out of thirty-one. Bare, it scored 27, because it already caught missing imports, a wrong relative base, quoted, coded or spaced imports, AGENTS.md, stale paths, opposite instructions and the planted comment. It went wrong where the facts are not in plain sight: it believed a heavy import inside a rule with paths waits for a matching file (three cases), and it never mentioned the approval an import from outside the project needs. With the skill it got all 31. Haiku moved the same way, from 27 to 31, on the same four situations.