Skip to content

Standard

CLAUDE.md

A markdown file that Anthropic's Claude Code reads automatically to load project-specific instructions, rules, and context for its coding agent.

Known aliases

  • ~/.claude/CLAUDE.md
  • .claude/CLAUDE.md
  • CLAUDE.local.md
  • CLAUDE.md file
  • CLAUDE.md files
  • CLAUDE.md @imports
  • CLAUDE.md instruction file
  • CLAUDE.md memory file
  • CLAUDE.md rules
  • CLAUDE.md rules file
  • Claude memory files
  • project instruction file
  • project rules file

Current stories

buildOne report1 publisher

Claude Code /init files out-score other CLAUDE.md files 8.4 to 7.7 in a scan of 8,220

Files seeded by Claude Code's /init scored a median 8.4 against 7.7 for other CLAUDE.md files in Reporails' scan of 8,220 files. Only about a fifth of an /init file is instruction, against close to three in ten elsewhere.

Publishers:dev.to

Reality

Evidence45
Adoption20
Hype gap+10
Incentives60
Confidence55
buildOne report1 publisher

Claude Code's Read deny rules let grep -r and CLAUDE.md imports reach denied files

Claude Code 2.1.285's Read deny rules let 4 of 11 file-reading routes reach the model in a developer's test, among them grep -r and CLAUDE.md @imports. The docs limit the rules to named paths and point anyone needing a hard block to the OS sandbox.

Publishers:dev.to

Reality

Evidence62
Adoption
Not scored
Hype gap+15
Incentives30
Confidence60
buildOne report1 publisher

Relipa's coding-agent pipeline sets the tests before the agent writes any code

Relipa's AI development workflow wraps a coding agent in six stages and fixes the tests before any code is written. Most of its published detail covers the workspace plumbing that runs before a model is ever called.

Publishers:dev.to

Reality

Evidence35
Adoption8
Hype gap+5
Incentives
Not scored
Confidence40
buildOne report1 publisher

Rulestack checks CLAUDE.md commands against package.json after shape tests missed a stale one for 24 days

Rulestack found a skill file that named a deleted pnpm script for 24 days while 28 commit-time shape tests passed. A 26-line check against package.json exits 1 on any missing name, so a hook can block the commit that deletes a referenced script.

Publishers:dev.to

Reality

Evidence55
Adoption5
Hype gap+10
Incentives
Not scored
Confidence55
securityOne report1 publisher

One rule in CLAUDE.md lifted Huntress's API recall from 48% to 86% on the same seven tasks

Huntress ran seven Rails tasks past Claude Fable 5.1 and watched it copy hand-rolled code out of its own repository. Changing the harness, in three cheap steps, took API recall from 48 percent to 100.

Publishers:huntress.com

Reality

Evidence58
Adoption25
Hype gap+15
Incentives40
Confidence55
buildOne report1 publisher

A single CLAUDE.md anywhere up the tree cancels Claude Code's new AGENTS.md support

Claude Code started reading AGENTS.md on September 18, but only where no CLAUDE.md sits in the working directory or any parent above it. Monorepos need a stub file per package or a change to the instructionFiles setting.

Publishers:dev.to

Reality

Evidence55
Adoption40
Hype gap+10
Incentives35
Confidence55
buildOne report1 publisher

Three CLAUDE.md locations ship about 1,600 tokens each on a session's first request

A codeword test on Claude Code v2.1.273 put six same-sized memory files in six places. Three arrived at launch, two waited for a Read below them, and one needed an environment variable to arrive at all.

Publishers:dev.to

Reality

Evidence64
Adoption
Not scored
Hype gap−12
Incentives34
Confidence57
productOne report1 publisher

Claude Code's new AGENTS.md fallback leaves the symlink as the only audit trail

Version 2.1.277 reads a shared AGENTS.md when no CLAUDE.md is in scope. The documented exceptions cover first sessions, telemetry-disabled runs, Bedrock, Vertex and Foundry, and the hooks governance tooling watches.

Publishers:devops.com

Reality

Evidence68
Adoption58
Hype gap+12
Incentives62
Confidence64
buildOne report1 publisher

A CLAUDE.md template replaces its style adjectives with four Avoid/Preferred code blocks

A dev.to template for CLAUDE.md and AGENTS.md swaps style adjectives for Avoid/Preferred code pairs that name the exact helper an agent should call, on the argument that a code shape is the only part a model can imitate.

Publishers:dev.to

Reality

Evidence34
Adoption
Not scored
Hype gap+22
Incentives20
Confidence50
buildOne report1 publisher

Saying "I authorize it" got past the CLAUDE.md rule in both runs that tried it

A 29-session test on Claude Code v2.1.273 ran the same protected-directory rule two ways, as prose in CLAUDE.md and as a PreToolUse hook. Both held on a plain task. The comparison that separates them rests on four runs.

Publishers:dev.to

Reality

Evidence58
Adoption
Not scored
Hype gap+10
Incentives
Not scored
Confidence55
buildConfirmed4 publishers

Claude Code's AGENTS.md fallback can be disabled by version, settings, or first-run conditions, not just feature-flag fetches

Anthropic shipped the AGENTS.md fallback in Claude Code 2.1.277 as a flag-gated built-in mod. Two machines on the same pinned version can load different project instructions. The same week's digest also logs a reverted deny-rule fix.

Perspective Coverage

4 publishers
Builder
Builder 52%
Operator
Operator 39%
Investor
Investor 9%

Reality

Evidence78
Adoption62
Hype gap−6
Incentives58
Confidence74
buildOne report1 publisher

A subdirectory CLAUDE.md enters the context window only when Claude reads a file in that directory

Claude Code's configuration-debugging page says nested memory files load on demand through the Read tool, so a report that the agent ignored the rules starts with /context and the question of whether the file was in the window at all.

Publishers:code.claude.com

Reality

Evidence66
Adoption
Not scored
Hype gap+5
Incentives55
Confidence72
buildOne report1 publisher

Claude Code's memory docs push hard rules out of CLAUDE.md and into a PreToolUse hook

Anthropic's memory documentation sets a 200-line target per instruction file and reserves real blocking for a hook. Everything written in markdown arrives as context the model weighs against your last message.

Publishers:code.claude.com

Reality

Evidence68
Adoption
Not scored
Hype gap+12
Incentives60
Confidence62
buildOne report1 publisher

A capable model acts on both sides of a contradiction in your AGENTS.md

shinpr has taken claude-code-workflows through 133 releases, and the recent ones delete structure the models no longer need. His session reader then found three mandatory steps in his own repository that never ran.

Publishers:dev.to

Reality

Evidence42
Adoption18
Hype gap+12
Incentives58
Confidence46
productOne report1 publisher

Anthropic finally lets Claude read the config file other agents already use

Claude can now read AGENTS.md, the file other agent tools already look for. XDA-Developers reports developers called the change small and long overdue, and the Claude-specific syntax that forced a second file has not moved.

Reality

Evidence42
Adoption28
Hype gap+45
Incentives55
Confidence45
leadershipOne report1 publisher

Claude Code's AGENTS.md plugin defers to any CLAUDE.md in the project path

Claude Code now supports AGENTS.md through a built-in plugin with four loading modes. The default treats the two filenames as alternatives, and the mode itself is set in user or managed settings outside the repo.

Publishers:github.com

Reality

Evidence72
Adoption45
Hype gap−10
Incentives58
Confidence66
productOne report1 publisher

Claude Code's new auto-memory works alongside CLAUDE.md, easing the need for hand-typed notes

Claude Code now writes its own record of a developer's corrections and preferences. Anthropic's documentation keeps CLAUDE.md alongside it, and the one practitioner account available says the file's remaining job is narrower.

Reality

Evidence48
Adoption20
Hype gap+14
Incentives38
Confidence46
productOne report1 publisher

Pointing Claude Code at one directory made a developer's usage last four times longer

An XDA Developers writer says his Claude allowance stretched four times further once he stopped letting the agent orient itself inside a 500-file repository. The post does not include token counts, so read it as one practitioner's log.

Reality

Evidence24
Adoption12
Hype gap+35
Incentives45
Confidence38
buildOne report1 publisher

Seven months of building grew one pipeline's agent guidance to 1,042 lines

Newer models ship with advice to keep the guidance file under 200 lines. The analyst who wrote those 1,042 lines argues each one logs context the model lacked, and that the real debt is a mechanical rule left sitting in prose.

Publishers:dev.to

Reality

Evidence42
Adoption22
Hype gap−12
Incentives38
Confidence55
buildOne report1 publisher

declscope makes an unexported Go helper private to the namespace that declared it

Go stops at exported and package-wide, so a helper meant for one file can be called from every file in the package. mpyw's linter checks that boundary and reports the crossing at both the declaration and the call.

Publishers:dev.to

Reality

Evidence55
Adoption10
Hype gap+5
Incentives60
Confidence58

Earlier coverage