diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 903afe3..cfa9db7 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -91,9 +91,18 @@ jobs:
           CTRLRUN_SOURCE: ${{ github.workspace }}/ctrlrun
         run: ./scripts/check.sh
 
-      # The four drift checks, named individually because `STYLE.md` says the CI job runs them
-      # and `test_ci_runs_the_three_checks_and_the_drift_check` reads this file to prove it.
+      # The drift checks, named individually because `STYLE.md` says the CI job runs them and
+      # `test_ci_runs_the_three_checks_and_the_drift_check` reads this file to prove it.
       # A guard CI does not run is prose.
+      #
+      # `render_readiness.py --check` joined them on 2026-09-14. Its own docstring called it
+      # "what CI runs" and CI did not run it, which is the same sentence one level up: the test
+      # count is the one figure on the site that is a measurement rather than a claim, and the
+      # pytest check on it compares the embedded block against the *stored* `readiness.json`
+      # rather than against the suite, so the two agreed with each other while both drifted away
+      # from the library. It cannot flap between a paired kernel and docs merge, because the
+      # count is a **floor**: it fails when the suite has fewer tests than the page claims, and
+      # passes when it has more.
       - name: The documentation audit
         working-directory: ctrlrun-docs
         env:
@@ -103,3 +112,4 @@ jobs:
           python tools/docs_audit/lint.py
           python tools/docs_audit/links.py
           python tools/docs_audit/render_capabilities.py --check
+          python tools/docs_audit/render_readiness.py --check
diff --git a/docs.mdx b/docs.mdx
index f343dd4..9ffb2d3 100644
--- a/docs.mdx
+++ b/docs.mdx
@@ -219,7 +219,7 @@ the framework's own interrupt, and a framework with no such primitive does not n
 
 {/* generated from the suite, pyproject and the soak (mdx) — run the generator */}
 - **Version 0.10.0**, on [PyPI](https://pypi.org/project/ctrlrun/), Python 3.11 and later, tested on 3.11 to 3.14.
-- **6,070 tests**, every version specified before it was written and every requirement mutation-tested.
+- **6,080 tests**, every version specified before it was written and every requirement mutation-tested.
 - **27 guarantees you can check in your own setup**, with `ctrlrun verify` against your policy, on your store's backend, in a scratch store it creates.
 - **One host: a file.** SQLite, no server, no ops. **Many hosts: Postgres**, the same guarantees, graded by the same suite.
 - **Soaked for 20m 0s on postgres**: 889,735 actions, 0 unattributed ambiguous outcomes, positive control fired. Nothing here establishes what only accumulates over days. [What it does not establish](https://ctrlrun.dev/docs/production/soak).
diff --git a/docs/production/index.mdx b/docs/production/index.mdx
index 1165fe8..20df822 100644
--- a/docs/production/index.mdx
+++ b/docs/production/index.mdx
@@ -28,7 +28,7 @@ need. `test_the_first_line_of_the_section_says_which_store_and_why` asserts the
 
 {/* generated from the suite, pyproject and the soak (full) — run the generator */}
 - **Version 0.10.0**, on [PyPI](https://pypi.org/project/ctrlrun/), Python 3.11 and later, tested on 3.11 to 3.14.
-- **6,070 tests**, every version specified before it was written and every requirement mutation-tested. [Read more](/docs/how-this-is-built).
+- **6,080 tests**, every version specified before it was written and every requirement mutation-tested. [Read more](/docs/how-this-is-built).
 - **27 guarantees you can check in your own setup**, with `ctrlrun verify` against your policy, on your store's backend, in a scratch store it creates. [Read more](/docs/security/verify-guarantees).
 - **One host: a file.** SQLite, no server, no ops. **Many hosts: Postgres**, the same guarantees, graded by the same suite. [Read more](/docs/production/postgres).
 - **Soaked for 20m 0s on postgres**: 889,735 actions, 0 unattributed ambiguous outcomes, positive control fired. Nothing here establishes what only accumulates over days. [Read more](/docs/production/soak).
diff --git a/docs/reference/api/banner.mdx b/docs/reference/api/banner.mdx
index 92e33ba..9f01813 100644
--- a/docs/reference/api/banner.mdx
+++ b/docs/reference/api/banner.mdx
@@ -5,7 +5,7 @@ description: "Log SPEC-v0.3 §6.5's observe banner, once per `Control`. An adapt
 
 {/* generated by tools/docs_audit/render_api.py from the docstrings — edit the docstring, never this page */}
 
-`ctrlrun.banner` — function, defined at `src/ctrlrun/adapter.py:475`
+`ctrlrun.banner` — function, defined at `src/ctrlrun/adapter.py:484`
 
 ```python
 from ctrlrun import banner
diff --git a/docs/reference/api/needs_approval.mdx b/docs/reference/api/needs_approval.mdx
index 86d5b20..eafed2c 100644
--- a/docs/reference/api/needs_approval.mdx
+++ b/docs/reference/api/needs_approval.mdx
@@ -13,7 +13,7 @@ from ctrlrun import needs_approval
 
 
 ```python
-def needs_approval(control: Control, action: str, arguments: Mapping[str, Any], *, resource: str | None = None) -> bool
+def needs_approval(control: Control, action: str, arguments: Mapping[str, Any], *, resource: str | None = None, task: str | None = None, hop: str | None = None) -> bool
 ```
 
 Does this call need a human? For a framework that asks before it invokes (SPEC-v0.5 §3.5).
@@ -42,6 +42,13 @@ it to belongs in the evidence log.
 matters: authority matches on resource patterns (SPEC-v0.3 §4.2), so a predicate that
 skipped it would evaluate a different action from the one that runs.
 
+`task` and `hop` are that same argument one frame further out (SPEC-v0.10 §9). Without them
+this predicate evaluates against the receiver's **whole candidate set** while `execute`
+evaluates against the hop **alone** (§2.3), so it answers "no human needed" for a call
+`execute` then refuses. That is not a wider grant -- `Control.execute` is the enforcement
+point and decides against the hop either way -- but it costs the framework its own approval
+item, and a human is not asked before an invocation that then fails.
+
 ## Next
 
 - [Python API index](/docs/reference/api/index).
diff --git a/generated/readiness.full.mdx b/generated/readiness.full.mdx
index 3fbafe3..f797016 100644
--- a/generated/readiness.full.mdx
+++ b/generated/readiness.full.mdx
@@ -1,6 +1,6 @@
 {/* generated from the suite, pyproject and the soak (full) — run the generator */}
 - **Version 0.10.0**, on [PyPI](https://pypi.org/project/ctrlrun/), Python 3.11 and later, tested on 3.11 to 3.14.
-- **6,070 tests**, every version specified before it was written and every requirement mutation-tested. [Read more](/docs/how-this-is-built).
+- **6,080 tests**, every version specified before it was written and every requirement mutation-tested. [Read more](/docs/how-this-is-built).
 - **27 guarantees you can check in your own setup**, with `ctrlrun verify` against your policy, on your store's backend, in a scratch store it creates. [Read more](/docs/security/verify-guarantees).
 - **One host: a file.** SQLite, no server, no ops. **Many hosts: Postgres**, the same guarantees, graded by the same suite. [Read more](/docs/production/postgres).
 - **Soaked for 20m 0s on postgres**: 889,735 actions, 0 unattributed ambiguous outcomes, positive control fired. Nothing here establishes what only accumulates over days. [Read more](/docs/production/soak).
diff --git a/generated/readiness.json b/generated/readiness.json
index d031ea6..24cdd23 100644
--- a/generated/readiness.json
+++ b/generated/readiness.json
@@ -18,6 +18,6 @@
     "positive_control": true,
     "unexplained": 0
   },
-  "tests": 6070,
+  "tests": 6080,
   "version": "0.10.0"
 }
diff --git a/generated/readiness.mdx b/generated/readiness.mdx
index fead10d..5d095a0 100644
--- a/generated/readiness.mdx
+++ b/generated/readiness.mdx
@@ -1,6 +1,6 @@
 {/* generated from the suite, pyproject and the soak (mdx) — run the generator */}
 - **Version 0.10.0**, on [PyPI](https://pypi.org/project/ctrlrun/), Python 3.11 and later, tested on 3.11 to 3.14.
-- **6,070 tests**, every version specified before it was written and every requirement mutation-tested.
+- **6,080 tests**, every version specified before it was written and every requirement mutation-tested.
 - **27 guarantees you can check in your own setup**, with `ctrlrun verify` against your policy, on your store's backend, in a scratch store it creates.
 - **One host: a file.** SQLite, no server, no ops. **Many hosts: Postgres**, the same guarantees, graded by the same suite.
 - **Soaked for 20m 0s on postgres**: 889,735 actions, 0 unattributed ambiguous outcomes, positive control fired. Nothing here establishes what only accumulates over days. [What it does not establish](https://ctrlrun.dev/docs/production/soak).
diff --git a/generated/readiness.readme.md b/generated/readiness.readme.md
index 4113bc2..2539a25 100644
--- a/generated/readiness.readme.md
+++ b/generated/readiness.readme.md
@@ -1,6 +1,6 @@
 <!-- generated from the suite, pyproject and the soak (readme) — run the generator -->
 - **Version 0.10.0**, on [PyPI](https://pypi.org/project/ctrlrun/), Python 3.11 and later, tested on 3.11 to 3.14.
-- **6,070 tests**, every version specified before it was written and every requirement mutation-tested.
+- **6,080 tests**, every version specified before it was written and every requirement mutation-tested.
 - **27 guarantees you can check in your own setup**, with `ctrlrun verify` against your policy, on your store's backend, in a scratch store it creates.
 - **One host: a file.** SQLite, no server, no ops. **Many hosts: Postgres**, the same guarantees, graded by the same suite.
 - **Soaked for 20m 0s on postgres**: 889,735 actions, 0 unattributed ambiguous outcomes, positive control fired. Nothing here establishes what only accumulates over days. [What it does not establish](https://ctrlrun.dev/docs/production/soak).
diff --git a/tests/test_docs_audit.py b/tests/test_docs_audit.py
index c1c4324..f70c19d 100644
--- a/tests/test_docs_audit.py
+++ b/tests/test_docs_audit.py
@@ -660,7 +660,16 @@ def test_ci_runs_the_three_checks_and_the_drift_check():
     """`STYLE.md` says the `docs` job runs them. A guard that CI does not run is prose."""
     workflow = (REPO_ROOT / ".github" / "workflows" / "ci.yml").read_text(encoding="utf-8")
 
-    for script in ("snippets.py", "lint.py", "links.py", "render_capabilities.py --check"):
+    for script in (
+        "snippets.py",
+        "lint.py",
+        "links.py",
+        "render_capabilities.py --check",
+        # The count is a measurement, and until 2026-09-14 nothing in CI re-took it: the pytest
+        # check compares the embedded block against the stored `readiness.json`, so the two
+        # agreed with each other while both drifted from the library.
+        "render_readiness.py --check",
+    ):
         assert f"python tools/docs_audit/{script}" in workflow, script