align skills with additive project policy

README.md

@@ -85,6 +85,12 @@ Implement the bounded frontend task and return proof.
 `access: read|write` selects reader/writer scheduling; it does not grant commands
 or tools. Definitions are frozen at startup, so restart Ink after changing one.
 
+Approved rows from `$HOME/.ink/policy` and ancestor project `.ink/policy` files are
+additive alternatives. A project file can introduce a command only through the
+normalized effective-policy digest approval; it is never trusted merely because it
+exists. Empty project policy adds nothing. Child/session policy and the immutable
+host floor may only narrow the approved durable rows.
+
 Current caveat: Ink records `policy:` as frozen metadata but does not yet read the
 named relative file into the child effective policy. Do not treat it as enforced.
 Use the `configure-ink-agent` skill for the exact boundary and blocker.

skills/audit-ink-cli/SKILL.md

@@ -40,9 +40,11 @@ changes belong to Ink's repository authority and implementation workflow.
   installed artifact identity and a demonstrably matching checkout's specification,
   tests, public help text, and source; label those findings as contract/source
   evidence rather than executed runtime proof.
-- Global and project policy files explain only their contribution. Effective
+- Approved global and ancestor-project rows are additive alternatives; each file
-  authority also depends on all policy layers, pinned executable and contract
+  explains only its contribution. Effective authority also depends on the approved
-  bytes, startup freezing, and session decisions.
+  normalized digest, restrictive child/session policy, the host floor, pinned
+  executable and contract bytes, startup freezing, and session decisions. Never
+  interpret a project file as automatically trusted.
 - Treat handovers, READMEs, examples, hidden source branches, and remembered argv
   as leads. Public help owns operator-facing commands; the specification owns intended
   behavior; tests and source establish current checkout behavior.

skills/configure-ink-agent/SKILL.md

@@ -83,7 +83,8 @@ policy. Therefore:
   those are already sufficient.
 
 This gate may be removed only after the provider launch path proves that the
-referenced bytes are pinned and conjoined into the child effective policy.
+referenced bytes are pinned and applied as a restriction to the child's inherited
+approved durable policy.
 
 ## Decision loop
 
@@ -107,8 +108,8 @@ referenced bytes are pinned and conjoined into the child effective policy.
 ## Behavior smoke
 
 Positive: “Create a frontend writer child with only formatter and file mutation
-authority” loads this skill and blocks until the named policy is actually
+authority” loads this skill and blocks until the named restrictive policy is
-conjoined or the parent frozen policy already supplies that exact boundary.
+actually enforced or the parent frozen policy already supplies that exact boundary.
 
 Negative: “Ask the existing reviewer to inspect this diff” does not load this
 skill; it is ordinary delegation.

skills/create-ink-tool/SKILL.md

@@ -194,7 +194,9 @@ exits, environment/config precedence, credential timing, dependencies, pattern
 semantics, and one realistic pipeline. Explicit help succeeds on stdout; usage
 errors fail on stderr. Selector help gives value grammar, canonicalization, and a
 least-authority policy row, including AND within one row and alternatives across
-rows.
+approved global and ancestor-project rows. Project rows are not automatically
+trusted: Ink freezes the normalized effective policy and requires digest approval;
+child/session policy and the host floor may only narrow it.
 
 Keep argv unsurprising: options before operands, `--` ends options, `-` denotes a
 natural stream, secrets never enter argv, and unknown, incompatible, or trailing

test/skills-smoke.sh

@@ -23,13 +23,20 @@ configure=$repo/skills/configure-ink-agent/SKILL.md
 grep 'access.*read.*write' "$configure" >/dev/null
 grep 'named agent policy is metadata-only' "$configure" >/dev/null
 grep 'no `INK_AGENT_HOME` contract' "$configure" >/dev/null
+grep 'applied as a restriction' "$configure" >/dev/null
 
 audit_cli=$repo/skills/audit-ink-cli/SKILL.md
 grep 'ink agent catalog' "$audit_cli" >/dev/null
 grep 'frozen `tool delegate` subject' "$audit_cli" >/dev/null
+grep 'additive alternatives' "$audit_cli" >/dev/null
+grep 'automatically trusted' "$audit_cli" >/dev/null
 
 create_tool=$repo/skills/create-ink-tool/SKILL.md
 grep 'stage/match/apply' "$create_tool" >/dev/null
 grep 'projection' "$create_tool" >/dev/null
+grep 'approved global and ancestor-project rows' "$create_tool" >/dev/null
+grep 'requires digest approval' "$create_tool" >/dev/null
+
+grep 'Empty project policy adds nothing' "$repo/README.md" >/dev/null
 
 printf 'ok\n'