diff --git a/.agents/README.md b/.agents/README.md
index 7a8631170e..1f4e2364c5 100644
--- a/.agents/README.md
+++ b/.agents/README.md
@@ -34,6 +34,39 @@ the "agentic devenv" (`--agentic`) from the technical guide, which
 runs the client outside devenv and wires it in over MCP — here the
 client lives inside the sandboxed devenv docker.
 
+The content lives at the paths the ecosystem agreed on: `AGENTS.md` at the
+repository root and the skills in this folder, `.agents/skills/`. Codex,
+opencode, Cursor, Zed, Amp, omp and pi read both without any setup.
+
+Claude Code reads `AGENTS.md` from 2.1.277, through the built-in
+`agents-md` plugin, but only in a project that has no instruction file of
+its own. A `CLAUDE.md`, `.claude/CLAUDE.md` or `CLAUDE.local.md` anywhere
+from the repository root down to your working directory hands the whole
+project back to `CLAUDE.md`, and this file's guidance stops arriving. Keep
+none of them here. Personal steering goes in `AGENTS.local.md`, or in
+`.claude/rules/*.md` and `~/.claude/CLAUDE.md`, which the plugin does not
+count and which therefore leave the project guidance in place.
+
+Skills are untouched by that plugin and still load from `.claude/skills`
+alone, which is not committed, so link it once per clone:
+
+```bash
+mkdir -p .claude && ln -s ../.agents/skills .claude/skills
+# or, with Node:
+npx skills add ./.agents/skills --agent claude-code
+```
+
+Below 2.1.277, and on Bedrock, Vertex and Foundry where the fallback has
+not arrived, add `ln -s AGENTS.md CLAUDE.md` and drop it once your client
+has the feature. The auto-update channel decides when that is: `latest`,
+the default, has it; `stable` runs about a week behind; Homebrew and the
+Linux packages update by hand. Personal skills go in
+`.agents/local/skills/<name>/`.
+
+Every one of those paths is gitignored, so your own files keep working and
+no checkout overwrites them. Inside the devenv, `ws0` sees the links from
+the live checkout, and `ws1` and above are seeded on their first sync.
+
 Unlike the agentic devenv, running the client inside the devenv
 docker gives it full access to the live environment: every
 dependency already resolved by the image, so the agent can write
diff --git a/.claude/skills b/.claude/skills
deleted file mode 120000
index 2b7a412b8f..0000000000
--- a/.claude/skills
+++ /dev/null
@@ -1 +0,0 @@
-../.agents/skills
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index 3ed13ac9e3..f076619f74 100644
--- a/.gitignore
+++ b/.gitignore
@@ -99,10 +99,13 @@ opencode.json
 *.iml
 /.claude
 /CLAUDE.md
+/CLAUDE.local.md
 /.playwright-mcp
 /.devenv/mcp/
 /opencode.json
 /.agents/plans
+/.agents/local/
+/AGENTS.local.md
 /.opencode/reports
 /.opencode/prompts
 /.ci-logs
diff --git a/AGENTS.md b/AGENTS.md
index 1a9db621d8..fa95b4c045 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -14,9 +14,9 @@
 - **Never pipe test output directly to filters** (`| head`, `| tail`, `| grep`, etc.).
   Always redirect to a file first: `command > /tmp/output.txt 2>&1`, then read/grep the file.
   This prevents hiding test failures. See `mem:testing` for details.
-- **`.claude/skills` is a symlink to `.agents/skills`.**
-  Edit skills only in their canonical location (`.agents/skills`); never edit
-  through `.claude/skills`.
+- **Read `AGENTS.local.md` after this file whenever it exists.** It carries
+  the developer's steering for this project and overrides this file on prose style and
+  workflow, but not on project policy, where instructions here prevail.
 - **Commit message body lines MUST wrap at ≤76 chars** (subject ≤70 chars) and
   the commit MUST pass `./scripts/check-commit` with exit code 0 before you
   consider it done. This is mechanically checked — do not eyeball it.
diff --git a/CLAUDE.md b/CLAUDE.md
deleted file mode 100644
index 9d165adb8a..0000000000
--- a/CLAUDE.md
+++ /dev/null
@@ -1,10 +0,0 @@
-Read and follow the instructions in `AGENTS.md`.
-
-Treat `AGENTS.md` as the canonical project instruction file.
-
-## Comments and docstrings
-
-Keep comments and docstrings brief. They must always describe what the code
-currently does (its behavior, invariants, non-obvious rationale) — never
-what changed, when it changed, or history like "originally reported" /
-"before this existed" / "used to be X".
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index a7aeac3f3f..b4e2618f4e 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -38,6 +38,22 @@ Center](https://help.penpot.app/).
 - **Issue tracker**: We use [GitHub Issues](https://github.com/penpot/penpot/issues)
   for public bugs and [Taiga](https://tree.taiga.io/project/penpot/) for
   internal project management. Changelog entries reference both.
+- **AI coding agents**: guidance lives in `AGENTS.md` and the skills in
+  `.agents/skills/`, which Codex, opencode, Cursor, Zed, Amp, omp and pi read
+  without setup. Claude Code reads `AGENTS.md` from 2.1.277, but only in a
+  project that has no instruction file of its own, so keep no `CLAUDE.md`,
+  `.claude/CLAUDE.md` or `CLAUDE.local.md` in your checkout: any one of them
+  hides this repository's guidance from your session. Skills still load from
+  `.claude/skills` alone, so link it once per clone with
+  `mkdir -p .claude && ln -s ../.agents/skills .claude/skills`, or with
+  `npx skills add ./.agents/skills --agent claude-code`. Below 2.1.277, and
+  on Bedrock, Vertex and Foundry where the fallback has not arrived, add
+  `ln -s AGENTS.md CLAUDE.md` and remove it once your client has the
+  feature. Personal instructions belong in `AGENTS.local.md`, personal
+  skills in `.agents/local/skills/`, and personal Claude steering in
+  `.claude/rules/*.md`, which Claude loads beside the project instructions
+  without switching the fallback off. Every one of these paths is
+  gitignored.
 
 ## Reporting Bugs
 
diff --git a/docs/technical-guide/developer/devenv.md b/docs/technical-guide/developer/devenv.md
index b5496abe2f..b3d2f5c0ec 100644
--- a/docs/technical-guide/developer/devenv.md
+++ b/docs/technical-guide/developer/devenv.md
@@ -90,6 +90,12 @@ the frontend's MCP flag) is copied into each workspace on its initial sync
 only. After that the developer maintains it in each workspace; subsequent
 `--sync` runs leave the workspace copy alone.
 
+The Claude Code skills link, `.claude/skills`, is seeded the same way: it is
+gitignored, so the sync does not carry it, and the first sync creates it as a
+link to `.agents/skills`. A workspace that already has that path keeps what it
+has. No `CLAUDE.md` is created, because Claude Code reads `AGENTS.md` itself
+in a project that has none.
+
 Stopping is equally flexible — each workspace is independent. Shared infra
 stops only when no instances remain running:
 
diff --git a/manage.sh b/manage.sh
index 76ef2b1415..b2463e41a2 100755
--- a/manage.sh
+++ b/manage.sh
@@ -511,6 +511,17 @@ function sync-workspace {
         install -D "$PWD/$cfg" "$workspace/$cfg"
     fi
 
+    # Initial seed of the Claude Code skills link. It is gitignored, so git
+    # ls-files does not list it, yet Claude Code reads skills from
+    # .claude/skills alone. Seeded only when absent: afterwards the
+    # workspace copy belongs to the user, who may keep their own. No
+    # CLAUDE.md is seeded: Claude Code reads AGENTS.md itself in a project
+    # that has none, and a CLAUDE.md here would switch that off.
+    if [[ ! -e "$workspace/.claude/skills" && ! -L "$workspace/.claude/skills" ]]; then
+        mkdir -p "$workspace/.claude"
+        ln -s ../.agents/skills "$workspace/.claude/skills"
+    fi
+
     (
         cd "$workspace"
         git switch -C "${instance}/${CURRENT_BRANCH}" >/dev/null