AGENTS.md vs Windsurf rules
Every comparison page on the web is a capability table someone wrote from the vendor docs in an afternoon. None of them can tell you how many real repositories ship each file, how long the median one runs, or how often two of them turn up in the same project. Those answers need a corpus, and RuleStack counts one every night.
| Format | AGENTS.md 2026-08-02 | Windsurf rules 2026-08-01 |
|---|---|---|
| Asserted — what the docs say it can express | ||
| File | AGENTS.md | .windsurf/rules/*.md |
| Status | open-standard | vendor |
| Cross-tool | Yes | No |
| Tools that read it |
|
|
| Frontmatter | No | Yes |
| Glob targeting | No | Yes |
| Imports other files | No | No |
| Nested / per-directory | Yes | No |
| Multiple files | Yes | Yes |
| User-level scope | No | Yes |
| When it applies | Always in scope; in a monorepo the nearest AGENTS.md to the edited file wins. | Four trigger modes in frontmatter: always_on, glob, model_decision, manual. The legacy single-file .windsurfrules is still read. |
| Size limits | None | Per-rule and total character caps apply; long rules are truncated rather than rejected. |
| Measured — counted from real repositories on 2026-08-03 | ||
| Repositories carrying it | 396 | 14 |
| Share of indexed repos | 57.0% | 2.0% |
| Files indexed | 1,366 | 102 |
| Median length (words) | 954 | 515 |
| 90th percentile length | 2,955 | 1,518 |
| Files naming commands | 42.9% | 37.3% |
| Files containing code | 36.5% | 70.6% |
| Median quality score | 52 | 58 |
| Median repository stars | 8,629 | 114 |
How often they turn up together
A capability table cannot answer this at all. Of the repositories carrying the first format, this is the share that also carry the second — counted, both directions, on 2026-08-03.
AGENTS.md + Windsurf rules
2026-08-0310
repositories carry both. That is 2.5% of everything with AGENTS.md, and 71.4% of everything with Windsurf rules.
What each one is for
AGENTS.md
2026-08-02A plain-markdown README for coding agents, deliberately unopinionated: no frontmatter, no globs, no vendor keys. That minimalism is why it became the one file a dozen different agents will read, and why it carries the least per-file targeting power of any format here.
Strengths
- Read by more agents than any other format — one file covers most of a team's tooling
- No schema to get wrong; a plain markdown file always parses
- Nested files let a monorepo scope instructions per package
Weaknesses
- No glob targeting — every rule is loaded for every file, spending context
- No imports, so shared rules must be duplicated across packages
- No frontmatter means no machine-readable metadata for tooling to act on
Windsurf rules
2026-08-01Cursor's activation model with a different vocabulary — trigger modes instead of rule types — plus hard character caps, which is the one place a format here will silently drop instructions rather than fail loudly.
Strengths
- Trigger modes give the same glob and on-demand targeting as Cursor rules
- Workspace and global rule scopes
Weaknesses
- Windsurf-only
- Character caps truncate silently — a long rule can be half-applied with no error
- No imports
