How Claude remembers your project changedmemory
Nearest release: v2.1.286, published 10 hours after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 30 Sep 2026 07:11 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 30 Sep 2026 07:37 UTC.
Upstream edited
Recorded here
Lines+14added
Lines−12removed
From line
73
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits28to this page, all time
#### Audit your instruction files
The whole hunk
from line 73, old and new numbered
/
from line 73
7373
7474### Write effective instructions
7575
76CLAUDE.md files are loaded into the context window at the start of every session, consuming tokens alongside your conversation. The [context window visualization](/docs/en/context-window) shows where CLAUDE.md loads relative to the rest of the startup context. Because they're context rather than enforced configuration, how you write instructions affects how reliably Claude follows them. Specific, concise, well-structured instructions work best.
76Claude treats CLAUDE.md files as context, not enforced configuration, so how you write instructions affects how reliably Claude follows them. Write instructions that are concrete enough to verify:
7777
78**Size**: target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence. If your instructions are growing large, use [path-scoped rules](#path-specific-rules) so instructions load only when Claude works with matching files. You can also split content into [imports](#import-additional-files) for organization, though imported files still load and enter the context window at launch.
79
80**Structure**: use markdown headers and bullets to group related instructions. Claude scans structure the same way readers do: organized sections are easier to follow than dense paragraphs.
81
82**Specificity**: write instructions that are concrete enough to verify. For example:
83
8478* "Use 2-space indentation" instead of "Format code properly"
8579* "Run `npm test` before committing" instead of "Test your changes"
8680* "API handlers live in `src/api/handlers/`" instead of "Keep files organized"
8781
88**Consistency**: if two rules contradict each other, Claude may pick one arbitrarily. Review your CLAUDE.md files, nested CLAUDE.md files in subdirectories, and [`.claude/rules/`](#organize-rules-with-claude/rules/) periodically to remove outdated or conflicting instructions. In monorepos, use [`claudeMdExcludes`](#exclude-specific-claude-md-files) to skip CLAUDE.md files from other teams that aren't relevant to your work.
82Keep your files short, organized, and consistent:
8983
90To have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output styles under `.claude/` and `~/.claude/`. It looks for problems such as instructions written for older models, references to files or commands that don't exist, and files that contradict each other. You get a report of findings and a set of proposed edits, and nothing in your files changes until you ask Claude to apply them.
84* **Size**: target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence. Move instructions that matter for only part of the codebase into [path-scoped rules](#path-specific-rules), which load only when Claude works with matching files. [Imports](#import-additional-files) help you organize a long file but don't reduce its context cost, because imported files also load at launch.
85* **Structure**: group related instructions under markdown headers and bullets. Organized sections are easier for Claude to follow than dense paragraphs.
86* **Consistency**: if two instructions contradict each other, Claude may pick one arbitrarily. Review your CLAUDE.md files, nested CLAUDE.md files in subdirectories, and [`.claude/rules/`](#organize-rules-with-claude/rules/) periodically to remove outdated or conflicting instructions. To have Claude find them for you, [run a prompt audit](#audit-your-instruction-files).
9187
92To audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides`](/docs/en/skills#override-skill-visibility-from-settings) or with [`disableBundledSkills`](/docs/en/settings-reference#disablebundledskills). `/doctor prompt-audit` requires Claude Code v2.1.283 or later.
88#### Audit your instruction files
89
90To have Claude check your instruction files for outdated or conflicting content, run `/doctor prompt-audit` in a session. Claude looks for problems such as instructions written for older models, references to files or commands that don't exist, and files that contradict each other. You get a report of findings with proposed edits, and nothing in your files changes until you ask Claude to apply them.
91
92By default, the audit covers your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output styles under `.claude/` and `~/.claude/`. To audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`.
93
94The audit runs through the bundled `/claude-api` skill. It's unavailable while that skill is turned off in [`skillOverrides`](/docs/en/skills#override-skill-visibility-from-settings) or with [`disableBundledSkills`](/docs/en/settings-reference#disablebundledskills). `/doctor prompt-audit` requires Claude Code v2.1.283 or later.
9395
9496### Import additional files
9597
No line in this hunk matches that.