@iceinvein/agent-skills 0.11.0 → 0.12.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@iceinvein/agent-skills",
-  "version": "0.11.0",
+  "version": "0.12.0",
   "description": "Install agent skills into AI coding tools",
   "author": "iceinvein",
   "license": "MIT",

package/skills/index.json

@@ -283,7 +283,7 @@
     "name": "sluice",
     "description": "Routes work by change shape into four channels (bypass, fast, main, deep) and applies only the rules each channel needs, so a one-line fix does not pay the cost of a multi-subsystem build. Carries seven rules as one-liners in the router and the full treatment in references read only on friction. Checks the finished plan with plan.sh validate rather than trusting it to memory, seeds the run state from it, keeps a deep run's task breakdown in .sluice/run.json so a statusline segment and one status command can answer where the run is, and closes each run with a ledger read out of the session transcript: elapsed, tools, tokens, and what each dispatched agent cost where the transcript recorded it. Claude Code only; stands down where the superpowers pipeline governs the repo.",
     "type": "prompt",
-    "version": "0.12.2"
+    "version": "0.13.0"
   },
   {
     "name": "temporal-coupling-detector",

package/skills/sluice/references/deep-channel.md

@@ -364,6 +364,17 @@ rule that holds across all of them is that a review never runs below the model
 that built the task, so tiers 1 and 2 over a downshifted task come back up to
 this session's.
 
+**Where the repo carries review tiering of its own, this table governs.** It is
+the more specific of the two: wired into `Flips`, the `Model` marks and the
+count pre-flight prices, so a repo's tiers cannot be honoured without unpicking
+those. The usual clash is a repo tier that buys a bigger model for its risky
+tasks, and it loses to the model rule above for the reason given there. What
+the repo keeps is everything this table does not cover, which is most of what
+such rules are for: its gate on deterministic checks before a task reports
+done, the shape of its skip ledger, what it does after a fix round that touched
+no logic. Take the dispatch decision from here and the rest from there, and say
+in the pre-flight count which side each came from.
+
 A task matching more than one row takes the highest tier of them. Tier is the
 number, not the row order and not which shape sounds more serious. A task that
 only creates files but ships prose is tier 2, and a suite re-bless paired with

package/skills/sluice/skill.json

@@ -1,6 +1,6 @@
 {
   "name": "sluice",
-  "version": "0.12.2",
+  "version": "0.13.0",
   "description": "Routes work by change shape into four channels (bypass, fast, main, deep) and applies only the rules each channel needs, so a one-line fix does not pay the cost of a multi-subsystem build. Carries seven rules as one-liners in the router and the full treatment in references read only on friction. Checks the finished plan with plan.sh validate rather than trusting it to memory, seeds the run state from it, keeps a deep run's task breakdown in .sluice/run.json so a statusline segment and one status command can answer where the run is, and closes each run with a ledger read out of the session transcript: elapsed, tools, tokens, and what each dispatched agent cost where the transcript recorded it. Claude Code only; stands down where the superpowers pipeline governs the repo.",
   "author": "iceinvein",
   "type": "prompt",