@victortomaili/skill-cli 0.6.9 → 0.7.0

package/CHANGELOG.md

@@ -11,6 +11,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Cursor adapter (`.cursor/rules` format) for `init -g` bootstrap.
 - Per-agent hook adapters for automatic `/X` triggering (push model).
 
+## [0.7.0] - 2026-07-08
+
+### Changed
+- PROPOSE is now a BLOCKING GATE (per user direction), replacing v0.6.9's
+  non-blocking behavior. The agent must ASK about every cost/style/speed skill in
+  one message, then STOP and WAIT for the answer BEFORE starting the actual task.
+  This kills the recurring "I'll just do the task first" rationalization — there is
+  no "do the task anyway" path. The one-turn wait is the point: the user decides
+  the trade-off before the agent starts. Updated both the AGENTS.md block and the
+  `skill active` footer.
+
 ## [0.6.9] - 2026-07-08
 
 ### Changed

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@victortomaili/skill-cli",
-  "version": "0.6.9",
+  "version": "0.7.0",
   "description": "Cross-agent skill manager — one global store, clean agent folders, activation via skill.config",
   "license": "MIT",
   "author": "Victor Tomaili <victor@tomaili.com>",

package/src/commands/defaults.js

@@ -42,13 +42,15 @@ export function cmdActive() {
   console.log()
   console.log(c.bold('→ For EACH skill above, decide in your reply:'))
   console.log(c.gray('    LOAD    moves CORRECTNESS/QUALITY → run ') + c.cyan('skill cat <name>') + c.gray(' now.'))
-  console.log(c.gray('    PROPOSE moves COST, STYLE, or SPEED → ASK "enable <name>?" at the TOP of your reply,'))
-  console.log(c.gray('            THEN do the task in the SAME reply. Asking is NON-BLOCKING. A trade-off is the'))
-  console.log(c.gray('            USER') + c.gray("'s decision; it moves an axis on EVERY reply, so NEVER skip and NEVER"))
-  console.log(c.gray('            say "not relevant here". Mentioning / noting / "available" is NOT asking.'))
+  console.log(c.gray('    PROPOSE moves COST, STYLE, or SPEED → ASK "enable <name>?" about ALL of them,'))
+  console.log(c.gray('            then STOP and WAIT for the answer. Do NOT start the task until they answer.'))
+  console.log(c.gray('            The wait is the POINT — a trade-off is the USER') + c.gray("'s decision; it moves an axis") )
+  console.log(c.gray('            on EVERY reply, so NEVER skip and NEVER say "not relevant here".'))
+  console.log(c.gray('            Mentioning / noting / "available" is NOT asking.'))
   console.log(c.gray('    SKIP    moves NONE of the above.'))
-  console.log(c.yellow('  ⚠ Broken-rule excuses: "not relevant here", "would delay the task",'))
-  console.log(c.yellow('    "user has a clear request", "I will just do the task". Each = ask instead.'))
+  console.log(c.yellow('  ⚠ Breaking the gate: starting the task before the user answers,'))
+  console.log(c.yellow('    "would delay it", "user has a clear request", "I will just do the task",'))
+  console.log(c.yellow('    "not relevant here". → ASK first, then wait.'))
 }
 
 // `skill default <name>` — mark a skill as a default (active by default in every

package/src/lib/agents-md.js

@@ -37,11 +37,13 @@ no discretion and no third option:
   "the user didn't request it", and "skip unless needed" are FORBIDDEN — each one
   is you STEALING the user's decision. Deciding a trade-off is not your role;
   surfacing it is. A line in a table is NOT proposing — you must actually ask.
-  PROPOSE IS NON-BLOCKING: put the question at the TOP of your reply, then DO the
-  task in the SAME reply — asking never delays anything, so "the task is the
-  priority", "the user has a clear request", and "asking would block/delay it" are
-  FORBIDDEN excuses to skip asking. Mentioning / noting / "available" is NOT asking;
-  you must ask a yes/no question (e.g. "Enable <name>?").
+  PROPOSE IS A GATE: ASK "Enable <name>?" (ask about ALL such skills in ONE message),
+  then STOP and WAIT for the user's answer. Do NOT start the actual task until they
+  answer (yes → apply it, no → proceed without). The one-turn wait is the POINT —
+  the user chooses the trade-off BEFORE you start — so "asking would delay the task",
+  "the user has a clear request", "I'll just do the task first", and "I'll mention it
+  and proceed" are FORBIDDEN: each is you deciding for the user. Mentioning / noting /
+  "available" is NOT asking — you must ASK a yes/no question and then wait.
 - moves none of the above → skip.
 When unsure if a skill moves an axis → PROPOSE (ask). LOADED \u2260 LISTED: a skill is
 loaded only if you \`cat\`-ed it this session — listing it, its \u2605, or its \`active\`