Harness spec: one path form, the file tools' texts, the list tree, skills

filesystem.md, spec 3.0.0-draft, and the CLI made to match:

- Paths: absolute in every answer except a result's bracket (context.md),
  which keeps the call's path. glob and grep now give full paths.
- A missing file is `No such file or directory: {path}` for every tool
  that needs it, with no hint after it: in a chat a hidden file must read
  as a missing one. The CLI's "does not exist. Use write to create it." and
  "Write it first." are gone; an edit of a directory is `Is a directory`,
  glob over a file `Not a directory`.
- write/edit refusals, exactly: "{path} exists and has not been read in
  this session. Read it first." and "{path} changed since you last read
  it. Read it again before changing it." (no "on disk"), absolute path.
- A listing sorts names in code-point order; `list` with a depth is a
  tree indented two spaces a level, marks as in a single listing, cut at
  400 lines with a line saying so.
- Skills: where they are found and in what order on each side (the
  session's own place first, the person's next, what is shared last), and
  the name rule ^[a-z0-9][a-z0-9-]{0,63}$ that skill_manage checks. The
  CLI no longer makes names with _ or .; such skills still load.

README's 3.0.0 notes say so; CHANGELOG [Unreleased].

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/hermes-layer.test.ts

@@ -45,6 +45,10 @@ describe("skills", () => {
     rmSync(join(paths.config, "skills"), { recursive: true, force: true })
     const c = ctx()
     await expect(skillManageTool.run({ operations: [{ action: "create", name: "Bad Name", content: "x" }] }, c)).rejects.toThrow("not a valid skill name")
+    // The spec's rule (filesystem.md, *Skills*): letters, digits and - only, up to 64.
+    await expect(skillManageTool.run({ operations: [{ action: "create", name: "snake_case", content: "x" }] }, c)).rejects.toThrow("not a valid skill name")
+    await expect(skillManageTool.run({ operations: [{ action: "create", name: "v1.2", content: "x" }] }, c)).rejects.toThrow("not a valid skill name")
+    await expect(skillManageTool.run({ operations: [{ action: "create", name: "a".repeat(65), content: "x" }] }, c)).rejects.toThrow("not a valid skill name")
     await expect(skillManageTool.run({ operations: [{ action: "create", name: "a", content: skill("b", "wrong name") }] }, c)).rejects.toThrow('must be "a"')
     const long = "Use when the build breaks on the CI runner and nobody knows why it happens."
     const r = await skillManageTool.run({ operations: [{ action: "create", name: "ci", category: "devops", content: skill("ci", long) }, { action: "write_file", name: "ci", file_path: "references/runner.md", file_content: "runner notes" }] }, c)