diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7a3f09e..e62e5e1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,8 @@
 # Changelog
 
-## Unreleased
+## 0.5.0 - Unreleased
+
+Targeted as `0.5.0` because the explicit-use policy is a post-`v0.4.0` routing behavior change.
 
 ### Changed
 
@@ -8,6 +10,11 @@
 - Replaced broad natural-language trigger examples with `$briefprint` invocation examples.
 - Added `disable-model-invocation: true` to the installable skill metadata for hosts that support manual-only skill invocation.
 - Documented the boundary between the static agent skill bundle and Briefprint runtime caches under `--cache-dir`.
+- Aligned README cache-dir examples, including benchmark receipts, under `.cache/briefprint`.
+
+### Validation
+
+- Recorded latest fetched `origin/main` GitHub Actions CI success in `VALIDATION.md`.
 
 ## 0.4.0 - 2026-07-05
 
diff --git a/README.ko.md b/README.ko.md
index c8e480a..08c5cfb 100644
--- a/README.ko.md
+++ b/README.ko.md
@@ -74,7 +74,7 @@ pip install -e ".[pdf]"  # PDF 텍스트 추출 helper
 python -m document_briefing_cache.cli run \
   --input examples/mixed_documents.json \
   --mode brief \
-  --cache-dir .cache \
+  --cache-dir .cache/briefprint \
   --summary-mode rules \
   --show-stats \
   --explain-cache
@@ -92,7 +92,7 @@ summarizer_calls: 0
 python -m document_briefing_cache.cli run \
   --input examples/mixed_documents.json \
   --mode action_items \
-  --cache-dir .cache \
+  --cache-dir .cache/briefprint \
   --summary-mode rules \
   --show-stats
 ```
@@ -122,7 +122,7 @@ Claude.ai description variant: Explicit-use cached briefings for supplied docume
 python -m document_briefing_cache.cli benchmark \
   --input examples/mixed_documents.json \
   --incremental-input examples/incident_update.json \
-  --cache-dir .cache/readme-benchmark \
+  --cache-dir .cache/briefprint/readme-benchmark \
   --fresh \
   --mode brief \
   --mode digest \
@@ -233,7 +233,7 @@ python -m document_briefing_cache.cli run \
 
 `--redact-pii`는 `basic-contact-v1` 프로필을 적용합니다. 이메일, 한국 휴대폰 번호, 미국 전화번호를 다루지만 완전한 PII 탐지기는 아닙니다.
 
-`--redact-secrets`는 `basic-secrets-v1` 프로필을 적용합니다. bearer tokens, API keys, webhook URLs, card-like values, secret-shaped JSON keys를 best-effort로 가립니다. Secret redaction is not included in --sensitive; 민감 문서에 비밀값이 들어갈 수 있으면 별도로 켜야 합니다.
+`--redact-secrets`는 `basic-secrets-v1` 프로필을 적용합니다. bearer tokens, API keys, webhook URLs, card-like values, secret-shaped JSON keys를 best-effort로 가립니다. 비밀값 마스킹은 `--sensitive`에 포함되지 않으므로, 민감 문서에 비밀값이 들어갈 수 있으면 별도로 켜야 합니다.
 
 `--redact-secrets`는 `session_id`처럼 운영 상관관계 분석에 쓰이는 값도 secret-shaped key 아래에 있으면 가릴 수 있습니다. 정확한 추적보다 비밀값 보호가 더 중요한 경우에 켜세요.
 
@@ -262,7 +262,7 @@ OPENAI_API_KEY="..." python -m document_briefing_cache.cli run \
   --llm-max-retries 2 \
   --llm-max-input-tokens 12000 \
   --llm-max-output-tokens 4000 \
-  --cache-dir .cache \
+  --cache-dir .cache/briefprint \
   --show-stats
 ```
 
diff --git a/README.md b/README.md
index f4ffd08..ba67ee2 100644
--- a/README.md
+++ b/README.md
@@ -74,7 +74,7 @@ Run the sample:
 python -m document_briefing_cache.cli run \
   --input examples/mixed_documents.json \
   --mode brief \
-  --cache-dir .cache \
+  --cache-dir .cache/briefprint \
   --summary-mode rules \
   --show-stats \
   --explain-cache
@@ -92,7 +92,7 @@ Render another format from the same cached document state:
 python -m document_briefing_cache.cli run \
   --input examples/mixed_documents.json \
   --mode action_items \
-  --cache-dir .cache \
+  --cache-dir .cache/briefprint \
   --summary-mode rules \
   --show-stats
 ```
@@ -122,7 +122,7 @@ This local benchmark was run on the current examples with the deterministic `rul
 python -m document_briefing_cache.cli benchmark \
   --input examples/mixed_documents.json \
   --incremental-input examples/incident_update.json \
-  --cache-dir .cache/readme-benchmark \
+  --cache-dir .cache/briefprint/readme-benchmark \
   --fresh \
   --mode brief \
   --mode digest \
@@ -262,7 +262,7 @@ OPENAI_API_KEY="..." python -m document_briefing_cache.cli run \
   --llm-max-retries 2 \
   --llm-max-input-tokens 12000 \
   --llm-max-output-tokens 4000 \
-  --cache-dir .cache \
+  --cache-dir .cache/briefprint \
   --show-stats
 ```
 
diff --git a/VALIDATION.md b/VALIDATION.md
index ef84068..5cd5bfd 100644
--- a/VALIDATION.md
+++ b/VALIDATION.md
@@ -1,6 +1,6 @@
 # Validation
 
-Last verified: 2026-07-05
+Last verified: 2026-07-06
 
 ## Environment
 
@@ -24,6 +24,8 @@ ruff check .
 - `python scripts\validate_skill.py --run-evals`: `OK: briefprint skill repository validated (24 test files, 9 eval cases, 10 trigger cases, 5 model benchmark cases)`
 - `ruff check .`: `All checks passed!`
 
+Latest fetched `origin/main` CI status was checked separately: GitHub Actions `CI` run `28759630346` completed successfully for `677057a` on 2026-07-06T00:07:29Z. This confirms the base branch status; the commands above remain the source-tree validation for the current checkout.
+
 `tests/test_distribution_smoke.py` remains opt-in and skips unless `DBC_RUN_INSTALLED_SMOKE=1` is set. CI or release validation should still build wheel and sdist artifacts, install each into a fresh virtual environment, and run the installed smoke test outside the repository root.
 
 Example artifact smoke flow: