codecall 1.0.0 → 1.1.0

package/README.md

@@ -21,23 +21,47 @@ prerequisite-ready learning step.
 
 ## Install
 
-Install once from GitHub to add the same `codecall` skill to both your local Codex
-and Claude Code skills directories:
+Codecall is available as a Codex plugin, a Claude Code plugin, or an npm
+standalone skill. Every option is local, requires no API key, and does not
+upload your code.
+
+### Codex plugin
 
 ```bash
-npm install -g https://github.com/GAURAV-1313/codecall/archive/refs/heads/main.tar.gz
+codex plugin marketplace add https://github.com/GAURAV-1313/codecall
+codex plugin add codecall@codecall
 ```
 
-Restart the relevant coding agent or open a new task so it reloads the installed
-skill. This package does not require an additional API key, and its install step
-does not upload your code.
+Restart Codex or open a new task, then invoke `$codecall`.
+
+### Claude Code plugin
+
+```text
+/plugin marketplace add https://github.com/GAURAV-1313/codecall
+/plugin install codecall@codecall
+/reload-plugins
+```
 
-When the package is published to npm, the equivalent registry command will be:
+The Claude marketplace plugin command is namespaced: `/codecall:codecall`.
+
+### npm standalone skill
 
 ```bash
 npm install -g codecall
 ```
 
+The global install automatically copies the standalone skill to both
+`~/.codex/skills/codecall/` and `~/.claude/skills/codecall/`. Restart the
+relevant coding agent or open a new task to reload it. The standalone Claude
+skill keeps the short `/codecall` command.
+
+The current release is [`codecall@1.1.0`](https://www.npmjs.com/package/codecall).
+To update a previous global installation:
+
+```bash
+npm update -g codecall
+```
+
 ## Use it in Codex
 
 After Codex completes an implementation, invoke:
@@ -56,28 +80,31 @@ with concepts covered, weak areas, and an estimated session mastery. The final
 summary also gives implementation-grounded points to remember and only the
 relevant edge cases to check before applying the pattern in another project.
 
-The installable skill source is in [`skill/`](skill/SKILL.md).
+The shared plugin source is in [`plugins/codecall/`](plugins/codecall/skills/codecall/SKILL.md).
 
 ## Use it in Claude Code
 
-After Claude Code completes an implementation, invoke:
+After Claude Code completes an implementation through the marketplace plugin,
+invoke:
 
 ```text
-/codecall
+/codecall:codecall
 ```
 
-Claude Code discovers personal skills from `~/.claude/skills/<skill-name>/SKILL.md`.
-The installer creates `~/.claude/skills/codecall/SKILL.md`, using the same
-Agent-Skills-standard instruction file as Codex. It uses Claude Code's current
-conversation and edits—there is no extra learning-model API to configure.
+Claude Code namespaces marketplace skills to avoid conflicts between plugins.
+If Codecall was installed globally from npm instead, invoke `/codecall` from
+`~/.claude/skills/codecall/SKILL.md`. Both paths use the same Agent-Skills-
+standard instruction file and current conversation—there is no extra
+learning-model API to configure.
 
 For a repository-level automatic, non-blocking recommendation, add the same
 rule below to `CLAUDE.md` rather than `AGENTS.md`.
 
 ### Automatic recommendation
 
-Codex and Claude Code can select the skill implicitly, but skills are not
-background event listeners. `$codecall` (Codex) and `/codecall` (Claude Code) are the
+Codex and Claude Code can select the skill implicitly, but plugins and skills
+are not background event listeners. `$codecall` (Codex), `/codecall:codecall`
+(Claude marketplace), and `/codecall` (npm standalone Claude install) are the
 dependable triggers in any repository.
 
 The policy is intentionally selective: it recommends only when an implementation
@@ -85,10 +112,10 @@ has one strong signal (for example a security boundary, integration, public
 contract, or architecture decision) or two moderate signals (such as a reusable
 pattern plus operational behavior). It skips cosmetic, documentation-only,
 mechanical, generated-only, dependency-only, and ordinary test-only work. The
-full policy is [installed with the skill](skill/references/trigger-policy.md).
+full policy is [installed with the plugin](plugins/codecall/skills/codecall/references/trigger-policy.md).
 
-To enable it in a project, copy the [Codex template](skill/references/AGENTS.codecall.md)
-into `AGENTS.md` or the [Claude Code template](skill/references/CLAUDE.codecall.md)
+To enable it in a project, copy the [Codex template](plugins/codecall/skills/codecall/references/AGENTS.codecall.md)
+into `AGENTS.md` or the [Claude Code template](plugins/codecall/skills/codecall/references/CLAUDE.codecall.md)
 into `CLAUDE.md`:
 
 ```md
@@ -138,7 +165,7 @@ Providers render `runtime.history(session.id)` as their native UI: `/codecall`,
 tool call, or a non-blocking post-task recommendation. Core workers never
 depend on a provider SDK.
 
-## What ships in v1.0.0
+## What ships in v1.1.0
 
 - append-only, typed session events and an explicit state machine;
 - progressive minimal context represented as evidence references;
@@ -148,6 +175,7 @@ depend on a provider SDK.
 - an adaptive teach → one MCQ → evaluate → reinforce/advance loop;
 - final transfer guidance: points to remember plus cross-project edge cases;
 - one shared skill installed for Codex and Claude Code;
+- Codex and Claude Code marketplace plugins backed by the same shared source;
 - an explainable strong/moderate auto-recommendation policy with session-local
   duplicate suppression;
 - pluggable worker and documentation-provider contracts;
@@ -167,5 +195,19 @@ npm run build
 npm test
 ```
 
+### Plugin development
+
+The canonical plugin lives in `plugins/codecall/`. Validate it before release:
+
+```bash
+python3 /Users/gaurav/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py plugins/codecall
+claude plugin validate ./plugins/codecall
+```
+
+After updating the Claude marketplace plugin, users refresh it with
+`/plugin marketplace update codecall` and `/reload-plugins`. Codex users refresh
+the configured marketplace with `codex plugin marketplace upgrade codecall` and
+reinstall `codecall@codecall` if needed.
+
 See [ARCHITECTURE.md](ARCHITECTURE.md) for the full design, privacy posture,
 event model, state machine, and planned provider integrations.

package/dist/install-skill.js

@@ -4,7 +4,7 @@ import { dirname, join } from "node:path";
 import { fileURLToPath } from "node:url";
 function packagedSkillSource() {
     const here = dirname(fileURLToPath(import.meta.url));
-    return join(here, "..", "skill");
+    return join(here, "..", "plugins", "codecall", "skills", "codecall");
 }
 function copySkill(destinationRoot) {
     const source = packagedSkillSource();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codecall",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "license": "MIT",
   "type": "module",
   "description": "Implementation-grounded adaptive learning skills for Codex and Claude Code.",
@@ -24,7 +24,7 @@
   },
   "files": [
     "dist",
-    "skill",
+    "plugins/codecall",
     "README.md",
     "ARCHITECTURE.md",
     "LICENSE"

package/plugins/codecall/.claude-plugin/plugin.json

@@ -0,0 +1,13 @@
+{
+  "name": "codecall",
+  "version": "1.1.0",
+  "description": "Adaptive implementation-grounded learning for Claude Code.",
+  "author": {
+    "name": "Gaurav",
+    "url": "https://github.com/GAURAV-1313"
+  },
+  "homepage": "https://www.npmjs.com/package/codecall",
+  "repository": "https://github.com/GAURAV-1313/codecall",
+  "license": "MIT",
+  "keywords": ["learning", "developer-education", "implementation"]
+}

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

@@ -0,0 +1,23 @@
+{
+  "name": "codecall",
+  "version": "1.1.0",
+  "description": "Adaptive implementation-grounded learning for Codex.",
+  "author": {
+    "name": "Gaurav",
+    "url": "https://github.com/GAURAV-1313"
+  },
+  "homepage": "https://www.npmjs.com/package/codecall",
+  "repository": "https://github.com/GAURAV-1313/codecall",
+  "license": "MIT",
+  "keywords": ["codex", "claude-code", "learning", "developer-education"],
+  "skills": "./skills/",
+  "interface": {
+    "displayName": "Codecall",
+    "shortDescription": "Learn from the implementation you just completed.",
+    "longDescription": "A consent-first, adaptive learning skill grounded in completed implementation work.",
+    "developerName": "Gaurav",
+    "category": "Productivity",
+    "capabilities": ["Interactive"],
+    "defaultPrompt": ["Teach me the implementation I just completed with Codecall."]
+  }
+}

package/{skill → plugins/codecall/skills/codecall}/SKILL.md

@@ -7,8 +7,9 @@ description: Start an adaptive, implementation-grounded learning session after c
 
 Use the active coding agent and its current conversation as the learning
 runtime. Do not call an external model, request an API key, or run a separate
-learning CLI. In Codex, invoke this skill as `$codecall`; in Claude Code, invoke
-it as `/codecall`.
+learning CLI. In Codex, invoke this skill as `$codecall`. In the Claude Code
+marketplace plugin, invoke it as `/codecall:codecall`; the npm standalone
+installer keeps `/codecall` available.
 
 ## Completion handoff
 
@@ -23,8 +24,9 @@ not treat skill metadata as a background scheduler.
 Before deciding whether to show a post-implementation card, read
 [references/trigger-policy.md](references/trigger-policy.md). Apply it only to
 completed implementations with inspectable task, conversation, or changed-file
-evidence. A manual `$codecall` or `/codecall` request always starts this skill's
-normal Start/Skip flow regardless of the automatic policy.
+evidence. A manual `$codecall`, `/codecall:codecall`, or standalone `/codecall`
+request always starts this skill's normal Start/Skip flow regardless of the
+automatic policy.
 
 Use the matching standing-instruction template when configuring a project:
 [references/AGENTS.codecall.md](references/AGENTS.codecall.md) for Codex or

package/{skill → plugins/codecall/skills/codecall}/references/CLAUDE.codecall.md

@@ -4,4 +4,5 @@ Before the normal final response for a completed implementation, read the
 installed codecall skill's `references/trigger-policy.md` and evaluate the
 change. When its outcome is `recommend`, present Start Learning / Skip and wait.
 Do not teach until Start Learning. For `optional` or `skip`, finish normally;
-`/codecall` always remains available.
+`/codecall:codecall` remains available through the marketplace plugin and
+`/codecall` remains available through the npm standalone installer.

package/{skill → plugins/codecall/skills/codecall}/references/trigger-policy.md

@@ -35,7 +35,8 @@ localized fixes. Skip test-only work unless it introduces a transferable test
 strategy, harness, boundary, or behavior.
 
 - `recommend`: show Start Learning / Skip and wait for consent.
-- `optional`: do not interrupt; leave `$codecall` and `/codecall` available.
+- `optional`: do not interrupt; leave `$codecall`, `/codecall:codecall`, and
+  standalone `/codecall` available.
 - `skip`: do nothing automatically.
 
 Manual invocation always remains available. Never request an API key or invoke