# CLAUDE.md

**Canonical:** https://apis.io/providers/claude-md/  
**APIs profiled:** 0

CLAUDE.md is the markdown-based project memory format used by Anthropic's Claude Code CLI to give the model persistent, session-spanning instructions about a codebase. CLAUDE.md files are plain markdown that Claude Code loads at the start of every session by walking up the directory tree from the working directory, picking up files at organization-managed, user (~/.claude/CLAUDE.md), project (./CLAUDE.md or ./.claude/CLAUDE.md), and local (./CLAUDE.local.md) scopes. The format supports an @path import syntax for composing files together (up to five hops, relative or absolute), HTML block comments that are stripped before injection, an AGENTS.md import pattern for compatibility with other agents, and a complementary .claude/rules/ directory of path-scoped markdown rules with YAML frontmatter. CLAUDE.md is the human-authored counterpart to Claude Code's auto memory at ~/.claude/projects/<project>/memory/MEMORY.md, which Claude writes itself.

## Kin Score — 8.6 / 100 (minimal)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 8.6).

| Facet | Score |
|---|---|
| Discoverability | 57.4 |
| Contract Quality | 11.3 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 0.0 |
| Developer Ergonomics | 0.0 |
| Commercial Clarity | 0.0 |
| Access Clarity | 0.0 |

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Tags

AI Agents, Claude Code, Coding Standards, Configuration, Developer Workflow, Markdown, Memory, Project Configuration, Standard

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/claude-md/). Scores are computed from the provider's own public artifacts under a published rubric.