@minhpnq1807/contextos 0.6.8 → 0.6.9

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.6.9
+
+- **Skill suggestion formatting:** ContextOS now renders automatic skill suggestions as plain skill names instead of `$skill-name`, preventing Codex from treating suggested skills as native skill activation requests. Explicit user-requested skills still preserve `$skill-name` syntax.
+
 ## 0.6.8
 
 - **Fallback context recovery:** Prompt-hook direct fallback now keeps ContextOS useful when `ctx-mcp` is unavailable by using indexed file text matches and lightweight evidence-based skill scoring instead of returning only workflows or an empty context.

package/README.md

@@ -716,7 +716,7 @@ If hooks fall back because `ctx-mcp` is unavailable or not hot yet, ContextOS st
 
 Use `ctx --config` to choose which prompt sections ContextOS injects and how many suggestions each section may show. Interactive `ctx setup` includes the same section picker and limit prompts, while `ctx setup --yes` keeps the current saved config for automation. The panel supports multiple selection with `Space` and persists the global choice in `~/.ctx/contextos/output-config.json`. Defaults are five suggested files, five skills, and five workflows; caps are 20 files, 10 skills, and 5 workflows. Disabling rules hides both critical and additional relevant rule sections; compliance metadata remains available for reports.
 
-Injected prompt sections are intentionally compact: rules show only detected rule text, files show a comma-separated inline list of basenames without paths, skills show unique `$skill-name` activations as a comma-separated inline list without descriptions, and workflows show names with their agent chain. Stop hooks persist reports silently; run `ctx report` or `ctx evidence` when you want the detailed compliance output.
+Injected prompt sections are intentionally compact: rules show only detected rule text, files show a comma-separated inline list of basenames without paths, skills show unique plain skill names as a comma-separated inline list without descriptions, and workflows show names with their agent chain. ContextOS only keeps `$skill-name` syntax for skills the user explicitly requested, so automatic suggestions do not collide with native agent skill activation. Stop hooks persist reports silently; run `ctx report` or `ctx evidence` when you want the detailed compliance output.
 
 Codex may flatten newlines in its `UserPromptSubmit hook (completed)` preview. The injected `additionalContext` payload remains multiline; this is a Codex preview display limitation.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@minhpnq1807/contextos",
-  "version": "0.6.8",
+  "version": "0.6.9",
   "description": "Task-aware AGENTS.md context injection and compliance reporting for Codex, Claude Code, and Antigravity.",
   "type": "module",
   "bin": {

package/plugins/ctx/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "ctx",
-  "version": "0.6.8",
+  "version": "0.6.9",
   "description": "Inject task-relevant AGENTS.md rules into Codex through plugin hooks.",
   "author": {
     "name": "ContextOS"

package/plugins/ctx/lib/scheduler.js

@@ -25,7 +25,7 @@ export function scheduleContext({
     sections.push(commaSection("Suggested files to check", formatFiles(relevantFiles)));
   }
   if (outputConfig.sections.skills && suggestedSkills.length) {
-    sections.push(inlineSection("Skills to activate for this task", suggestedSkills.map(formatSkill)));
+    sections.push(inlineSection("Suggested skills for this task", suggestedSkills.map(formatSkill)));
   }
   if (outputConfig.sections.workflows && suggestedWorkflows.length) {
     sections.push(section("Suggested workflow for this task", suggestedWorkflows.map(formatWorkflow)));
@@ -98,7 +98,9 @@ function formatFile(file, basenameCounts) {
 
 function formatSkill(skill) {
   const name = String(skill.name || "").trim();
-  return name.startsWith("$") ? name : `$${name}`;
+  if (!name) return "";
+  if (name.startsWith("$")) return name;
+  return skill.explicit ? `$${name}` : name;
 }
 
 function formatWorkflow(workflow) {

package/.codex/skills/contextos-community/SKILL.md

@@ -1,15 +0,0 @@
----
-name: ContextOS Community
-description: Maintain Community Skill Packs, certification docs, launch demos, and distribution-oriented ContextOS assets.
----
-
-# ContextOS Community
-
-Use this skill for Community Skill Packs, ContextOS Ready certification, launch demos, roadmap docs, and contributor-facing assets.
-
-## Workflow
-
-1. Keep community assets small and PR-friendly.
-2. Prefer docs, examples, and tests over hosted infrastructure.
-3. Ensure every skill pack has triggers, evidence, negative triggers, and workflow.
-4. Validate docs and package inclusion before committing.

package/.codex/skills/contextos-community/skill.yaml

@@ -1,20 +0,0 @@
-id: contextos-community
-name: ContextOS Community
-description: Maintain Community Skill Packs, certification docs, launch demos, and distribution assets.
-positive_triggers:
-  prompts: [community skill packs, contextos ready, certified, badge, roadmap, launch demo, contributor]
-  files: [community-skills/README.md, docs/roadmap.md, docs/launch-demos.md, README.md]
-  dependencies: [vitest]
-evidence:
-  files: [community-skills/README.md, docs/roadmap.md, README.md]
-  dependencies: [vitest]
-negative_triggers:
-  prompts: [runtime scorer, mcp transport, embedding model]
-workflow:
-  - Keep community assets small and PR-friendly.
-  - Prefer docs, examples, and tests over hosted infrastructure.
-  - Ensure every skill pack has triggers, evidence, negative triggers, and workflow.
-  - Validate docs and package inclusion before committing.
-related_skills:
-  - community-management
-  - technical-writing

package/.codex/skills/contextos-release/SKILL.md

@@ -1,15 +0,0 @@
----
-name: ContextOS Release
-description: Prepare ContextOS npm package releases, changelog updates, plugin validation, tags, and GitHub release safety checks.
----
-
-# ContextOS Release
-
-Use this skill when bumping versions, preparing changelog entries, validating package contents, or publishing ContextOS.
-
-## Workflow
-
-1. Update README and CHANGELOG before tagging.
-2. Verify package and plugin versions stay aligned.
-3. Run build, plugin validation, MCP smoke, tests, and `npm pack --dry-run`.
-4. Commit, tag, push, and verify the GitHub release/npm publish path.

package/.codex/skills/contextos-release/skill.yaml

@@ -1,20 +0,0 @@
-id: contextos-release
-name: ContextOS Release
-description: Prepare ContextOS npm releases, changelog updates, tags, and package validation.
-positive_triggers:
-  prompts: [release, bump version, changelog, npm publish, tag, package, validate plugin]
-  files: [package.json, plugins/ctx/.codex-plugin/plugin.json, CHANGELOG.md, README.md]
-  dependencies: [vitest]
-evidence:
-  files: [package.json, plugins/ctx/.codex-plugin/plugin.json, CHANGELOG.md]
-  dependencies: [vitest]
-negative_triggers:
-  prompts: [application feature, dashboard UI, backend API]
-workflow:
-  - Update README and CHANGELOG before tagging.
-  - Verify package and plugin versions stay aligned.
-  - Run build, plugin validation, MCP smoke, tests, and npm pack dry-run.
-  - Commit, tag, push, and verify release automation.
-related_skills:
-  - npm-package-release
-  - github-actions-ci-cd

package/.codex/skills/contextos-routing/SKILL.md

@@ -1,15 +0,0 @@
----
-name: ContextOS Routing
-description: Work on ContextOS rule, file, skill, workflow, and evidence routing without adding broad runtime complexity.
----
-
-# ContextOS Routing
-
-Use this skill when changing ContextOS routing behavior, prompt hook output, scoring, evidence, or MCP scorer paths.
-
-## Workflow
-
-1. Inspect the existing routing module before changing behavior.
-2. Keep prompt-hook hot paths bounded and fail-open.
-3. Add focused tests for ranking, output, or telemetry behavior.
-4. Run `npm test`, `npm run build`, and `npm run validate:plugin` when the change affects runtime.

package/.codex/skills/contextos-routing/skill.yaml

@@ -1,20 +0,0 @@
-id: contextos-routing
-name: ContextOS Routing
-description: Work on ContextOS rule, file, skill, workflow, and evidence routing.
-positive_triggers:
-  prompts: [contextos routing, prompt hook, skill router, workflow router, evidence, scoring, ctx-mcp]
-  files: [plugins/ctx/lib/score-context.js, plugins/ctx/lib/skill-discoverer.js, plugins/ctx/lib/workflow-discoverer.js, plugins/ctx/lib/prompt-hook.js]
-  dependencies: [@modelcontextprotocol/sdk]
-evidence:
-  files: [plugins/ctx/lib/score-context.js, plugins/ctx/lib/skill-discoverer.js, plugins/ctx/mcp/server.js]
-  dependencies: [@modelcontextprotocol/sdk, @xenova/transformers]
-negative_triggers:
-  prompts: [dashboard, cloud service, hosted marketplace]
-workflow:
-  - Inspect the existing routing module before changing behavior.
-  - Keep prompt-hook hot paths bounded and fail-open.
-  - Add focused tests for ranking, output, or telemetry behavior.
-  - Run npm test plus build and plugin validation for runtime changes.
-related_skills:
-  - mcp-tool-developer
-  - agent-memory-mcp