@victortomaili/skill-cli 0.5.0 → 0.5.1

package/CHANGELOG.md

@@ -11,6 +11,19 @@ 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).
 
+## [0.5.1] - 2026-07-07
+
+### Fixed
+- AGENTS.md bootstrap block hardened into hard rules after a live pi-agent test
+  surfaced two gaps. **(a) START GATE:** on the first user message, the agent's
+  VERY FIRST action — BEFORE ANYTHING ELSE (before thinking, before any tool call)
+  — MUST be `skill defaults` + `skill cat <name>` for each, then `skill list`
+  (discovery is mandatory, not optional). **(b) Context-altering = PROPOSE-ONLY:**
+  `active` / ★-default means *available*, not *applied* — propose ≠ auto-apply,
+  and the rule overrides any other skill's "always use" instruction. Also:
+  whenever a skill is loaded mid-session, re-evaluate the message and load/propose
+  any newly-relevant one.
+
 ## [0.5.0] - 2026-07-07
 
 ### Added

package/README.md

@@ -196,13 +196,13 @@ default; `space` toggles the per-project override.
 `skill init -g` injects a short, idempotent block into each detected agent's global
 instruction file (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`):
 
-> On session start, run `skill defaults` and load each with `skill cat <name>`.
-> Skills are NOT in context until you load them — each message, decide whether one
-> is relevant and load it (`skill cat <name>` / `skill trigger <keyword>`); load each
-> only once. A skill that changes HOW you respond (output style/mode) is PROPOSED,
-> not auto-applied — apply only after the user confirms (an explicit `/X` counts).
-> When the user types `/X`, run `skill trigger X` — single match → apply; multiple →
-> show candidates.
+> **START GATE:** on the first user message, your VERY FIRST action — BEFORE
+> ANYTHING ELSE (before thinking, before any tool call) — is `skill defaults` +
+> `skill cat <name>` for each, then `skill list`. Then each
+> message, discover/load relevant skills (`skill cat` / `skill trigger`), once each.
+> A **context-altering** skill (changes HOW you respond — style/mode) is
+> **PROPOSE-ONLY**: propose it, then apply only after the user confirms
+> (`active` ≠ applied; an explicit `/X` counts). `/X` → `skill trigger X`.
 
 It's wrapped in `<!-- BEGIN skill-cli --> … <!-- END skill-cli -->` markers, never
 duplicates, and preserves your existing file content. Re-run `init -g` any time —

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@victortomaili/skill-cli",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "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/lib/agents-md.js

@@ -16,24 +16,32 @@ NOT copied into agent directories (\`~/.claude\`, \`~/.codex\`, etc.) — so the
 won't appear here.
 
 Usage:
-- \`skill list\` — skills installed and active in the current project
+- \`skill list\` — skills installed + active in the current project (with triggers)
 - \`skill show <name>\` — skill summary (path, triggers, version)
 - \`skill cat <name>\` — load skill content into context
+- \`skill default <name>\` — mark a skill as a global default (active + auto-load)
 
-Defaults: on session start, run \`skill defaults\` to list skills marked as
-defaults (active by default + auto-load), then \`skill cat <name>\` for each. Mark
-your own with \`skill default <name>\` (global — active in every project).
+START GATE (mandatory): On the FIRST user message of a session, your VERY FIRST
+action — BEFORE ANYTHING ELSE: before you start thinking/reasoning about the task
+and before any tool call — MUST be to run \`skill defaults\` then
+\`skill cat <name>\` for each result, then \`skill list\` to learn every skill's
+triggers. Do this even if the task looks trivial: skills shape how you should
+approach the task, so you cannot reason about it correctly until they are loaded.
 
-Discovery: skills are NOT used unless you load them — never assume a skill is
-already in context. On each user message, decide whether a skill is relevant to
-the task (match the message against a skill's triggers/topic); if one is relevant
-AND not yet loaded, load it with \`skill cat <name>\` (or \`skill trigger <keyword>\`
-to resolve a keyword to a skill). Load each skill only ONCE per session.
+Discovery (mandatory, every message): On EVERY user message, decide whether a
+skill is relevant by matching the message against the trigger catalog from
+\`skill list\`. If a relevant skill is not yet loaded, load it with \`skill cat
+<name>\` (or \`skill trigger <keyword>\` to resolve a keyword). Load each skill only
+ONCE per session. When you load or re-read ANY skill mid-session, immediately
+re-evaluate the current message and load/propose any newly-relevant skill.
 
-Context-altering skills: some skills change HOW you respond — output style, tone,
-format, or a persistent mode (e.g. a terseness/compression style) — rather than
-just adding task knowledge. Do NOT auto-apply these. PROPOSE the skill and apply
-it only after the user confirms; an explicit \`/X\` trigger counts as confirmation.
+Context-altering skills (HARD RULE): Some skills change HOW you respond — output
+style, tone, format, or a persistent mode (e.g. a terseness/compression style) —
+rather than just adding task knowledge. These are PROPOSE-ONLY. You MUST propose
+such a skill and apply it ONLY after the user confirms; an explicit \`/X\` trigger
+counts as confirmation. \`active\` / \u2605-default means AVAILABLE, not APPLIED —
+propose \u2260 auto-apply. This rule overrides any other skill's "always use" rule for
+context-altering skills.
 
 Triggers: when the user types \`/X\`, run \`skill trigger X\`.
 - Single match → apply the output directly.