diff --git a/docs/superpowers/specs/2026-07-16-context-compaction-overhaul-design.md b/docs/superpowers/specs/2026-07-16-context-compaction-overhaul-design.md
index 3a859cb..61d70ec 100644
--- a/docs/superpowers/specs/2026-07-16-context-compaction-overhaul-design.md
+++ b/docs/superpowers/specs/2026-07-16-context-compaction-overhaul-design.md
@@ -135,9 +135,13 @@ Runs every turn, unconditionally, before token counting — not gated on `should
 pub fn apply(tool_name: &str, output: &str) -> String
 ```
 
-Size floor: outputs under 1500 bytes pass through unchanged (compression only pays off on
-large output, and touching small results risks losing detail with no token benefit).
-Above the floor, dispatch by content shape:
+`read` is exempted entirely, always passed through unchanged regardless of size: its output
+must stay byte-exact because the agent relies on it for exact-match edits afterward, and a
+squashed view of a JSON config file (or any file whose content happens to parse as JSON)
+would otherwise be silently altered. Size floor for every other tool: outputs under 1500
+bytes pass through unchanged (compression only pays off on large output, and touching small
+results risks losing detail with no token benefit). Above the floor, dispatch by content
+shape:
 
 - `squash_json(&str) -> String` — hand-rolled JSON tokenizer; structural tokens (keys,
   brackets, colons, commas, booleans, null) always kept; string values kept if ≤20 chars or