a11y-loop 0.2.0 → 0.2.2

package/.claude-plugin/marketplace.json

@@ -0,0 +1,40 @@
+{
+  "name": "chanmeng-a11y-loop",
+  "owner": {
+    "name": "Chan Meng",
+    "url": "https://github.com/ChanMeng666"
+  },
+  "metadata": {
+    "description": "Makes AI coding agents decide accessibility while the work is still being planned and write accessible UI by default, then verify it in a real browser across the states they built — and say exactly what could not be checked. Ships the a11y-loop Agent Skill, a /a11y-plan command, and a plan-mode gate that declines a UI plan with no accessibility content in it.",
+    "version": "0.2.2"
+  },
+  "plugins": [
+    {
+      "name": "a11y-loop",
+      "source": "./",
+      "version": "0.2.2",
+      "description": "Accessibility in the plan, not after the pull request. Adds §0 plan rules (conformance target, per-component criteria, the product decisions that foreclose accessibility, color tokens before components), standing WCAG 2.2 AA generation rules, and a PreToolUse hook on ExitPlanMode that declines a UI-touching plan with no accessibility content — once, handing back the section to fill in. Verification is the a11y-loop CLI: axe-core in Chromium across default, dark, forced-colors, reduced-motion and 320px passes.",
+      "author": {
+        "name": "Chan Meng",
+        "url": "https://github.com/ChanMeng666"
+      },
+      "homepage": "https://ChanMeng666.github.io/a11y-loop/",
+      "repository": "https://github.com/ChanMeng666/a11y-loop",
+      "license": "MIT",
+      "keywords": [
+        "accessibility",
+        "a11y",
+        "wcag",
+        "wcag22",
+        "axe-core",
+        "playwright",
+        "plan-mode",
+        "agent-skills",
+        "aria",
+        "contrast",
+        "screen-reader",
+        "audit"
+      ]
+    }
+  ]
+}

package/.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "a11y-loop",
   "displayName": "a11y-loop",
-  "version": "0.2.0",
+  "version": "0.2.2",
   "description": "Hard-gates plan mode: a plan that changes UI has to say what it decided about accessibility before it can be approved. Ships the a11y-loop skill and a /a11y-plan command alongside it.",
   "author": {
     "name": "Chan Meng",
@@ -21,7 +21,5 @@
     "hooks",
     "agent-skills"
   ],
-  "skills": "./skill/",
-  "commands": "./commands/",
-  "hooks": "./hooks/hooks.json"
+  "skills": "./skill/"
 }

package/README.md

@@ -335,7 +335,36 @@ secondary format for tools that consume it.
 - Node.js ≥ 20
 - A Chromium install for Playwright (installed in the steps below)
 
-### Installation
+> **Point your agent at this section.** Every command below is non-interactive, idempotent, and
+> safe to re-run — no prompts, no TTY, no menus. An agent can install and verify the whole thing
+> without asking you to click anything. The one exception is called out explicitly at the end.
+
+### Install everything (agent-runnable, one block)
+
+```bash
+npm i -g a11y-loop
+npx playwright install chromium
+mkdir -p ~/.claude/skills
+cp -r "$(npm root -g)/a11y-loop/skill/a11y-loop" ~/.claude/skills/
+claude plugin marketplace add ChanMeng666/a11y-loop
+claude plugin install a11y-loop@chanmeng-a11y-loop --scope user
+```
+
+That is: the CLI, its browser, the portable skill, and the optional Claude Code plugin. No `git
+clone` — the skill ships inside the npm package. Verify:
+
+```bash
+a11y-loop --version
+test -f ~/.claude/skills/a11y-loop/references/plan-phase.md && echo "skill ok"
+claude plugin list | grep -A2 'a11y-loop@'   # expect: Status: ✔ enabled
+```
+
+Skip the last two lines if you only want the portable skill, or the `mkdir`/`cp` pair if you only
+want the plugin. Do not do both: the plugin carries its own copy, so the model ends up seeing
+`a11y-loop` *and* the directory-qualified `a11y-loop:a11y-loop`, paying the always-on token cost
+twice. If both names show up, delete `~/.claude/skills/a11y-loop` and keep the plugin.
+
+### Installation (details)
 
 ```bash
 # Run it directly, no install
@@ -363,18 +392,22 @@ browser) — e.g. `PLAYWRIGHT_BROWSERS_PATH=D:\playwright-browsers`.
 
 ### Installing the Agent Skill
 
-Copy the skill directory into any Agent Skills-compatible client:
+The skill is a directory. Copy it wherever your client reads skills from — no clone required, since
+`npm i -g a11y-loop` already put it on disk:
 
 ```bash
+SKILL_SRC="$(npm root -g)/a11y-loop/skill/a11y-loop"
+
 # Personal, all projects (Claude Code and other clients that read ~/.claude/skills)
-cp -r skill/a11y-loop ~/.claude/skills/a11y-loop
+mkdir -p ~/.claude/skills && cp -r "$SKILL_SRC" ~/.claude/skills/
 
-# Or project-scoped
-cp -r skill/a11y-loop .claude/skills/a11y-loop
+# Or project-scoped, committed with the repo
+mkdir -p .claude/skills && cp -r "$SKILL_SRC" .claude/skills/
 ```
 
-Any client implementing the [Agent Skills specification](https://agentskills.io/specification)
-can load it the same way — Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, and more.
+From a checkout, `skill/a11y-loop` is the same directory. Any client implementing the
+[Agent Skills specification](https://agentskills.io/specification) loads it the same way — Claude
+Code, Cursor, GitHub Copilot, Codex, Gemini CLI, and more. Re-running the copy upgrades in place.
 
 ### Optional: the Claude Code plugin layer
 
@@ -383,10 +416,37 @@ Claude-Code-only layer that adds one thing the portable skill cannot do — enfo
 plan mode:
 
 ```bash
-# From a checkout, in Claude Code
-/plugin install .
+claude plugin marketplace add ChanMeng666/a11y-loop
+claude plugin install a11y-loop@chanmeng-a11y-loop --scope user
+```
+
+Both are ordinary CLI commands — no TTY, no prompts, safe to re-run. (They also exist as `/plugin
+marketplace add …` and `/plugin install …` inside a session, but an agent should use the CLI form.)
+Managing it later is equally non-interactive: `claude plugin disable a11y-loop`, `claude plugin
+enable a11y-loop`, `claude plugin uninstall a11y-loop@chanmeng-a11y-loop` — add `-y` only if you
+pass `--prune`, which is the single flag that asks for confirmation.
+
+From a local checkout, `claude plugin marketplace add ./` registers the working copy instead, so the
+plugin tracks your edits rather than the published repo.
+
+**Team-wide, declaratively.** `--scope project` writes `.claude/settings.json`, which you commit —
+after that a clone needs no install commands at all:
+
+```json
+{
+  "extraKnownMarketplaces": {
+    "chanmeng-a11y-loop": { "source": { "source": "github", "repo": "ChanMeng666/a11y-loop" } }
+  },
+  "enabledPlugins": { "a11y-loop@chanmeng-a11y-loop": true }
+}
 ```
 
+**The one thing an agent cannot do for you.** Project-scoped plugins and hooks are gated behind
+Claude Code's workspace-trust prompt the first time that directory is opened. That is a deliberate
+security boundary in Claude Code — code from a repo should not execute because a file said so — and
+nothing here can or should bypass it. `--scope user` avoids it entirely, which is why the
+agent-runnable block above uses user scope.
+
 It contributes:
 
 - a `PreToolUse` hook matched to `ExitPlanMode`. When a plan changes UI work and says nothing about
@@ -403,7 +463,7 @@ and a human.
 
 | | Portable skill | Plugin layer |
 |---|---|---|
-| Install | copy `skill/a11y-loop` | `/plugin install .` |
+| Install | copy `skill/a11y-loop` | `claude plugin install a11y-loop@…` |
 | Works in | 40+ Agent Skills clients | Claude Code only |
 | Gives you | §0 planning, §1 generation, §2 the loop, §3 honest reporting | plan-mode enforcement, `/a11y-plan` |
 | Required? | yes | no |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "a11y-loop",
-  "version": "0.2.0",
+  "version": "0.2.2",
   "description": "Makes AI coding agents decide accessibility while the work is still being planned and write accessible UI by default, then proves what it can prove with a real browser audit across the states they built — and tells you exactly what it could not check.",
   "type": "module",
   "bin": {

package/skill/a11y-loop/SKILL.md

@@ -28,7 +28,7 @@ compatibility: >-
   The generation and honesty rules apply with or without the CLI; every step
   that says "audit" requires it.
 metadata:
-  "a11y-loop/version": "0.2.0"
+  "a11y-loop/version": "0.2.2"
 allowed-tools: 'Bash(a11y-loop *) Bash(npx a11y-loop *) Bash(node ${CLAUDE_SKILL_DIR}/../../src/cli.js *)'
 ---