a11y-loop 0.2.0 → 0.2.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "chanmeng-a11y-loop",
|
|
3
|
+
"owner": {
|
|
4
|
+
"name": "Chan Meng",
|
|
5
|
+
"url": "https://github.com/ChanMeng666"
|
|
6
|
+
},
|
|
7
|
+
"metadata": {
|
|
8
|
+
"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.",
|
|
9
|
+
"version": "0.2.1"
|
|
10
|
+
},
|
|
11
|
+
"plugins": [
|
|
12
|
+
{
|
|
13
|
+
"name": "a11y-loop",
|
|
14
|
+
"source": "./",
|
|
15
|
+
"version": "0.2.1",
|
|
16
|
+
"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.",
|
|
17
|
+
"author": {
|
|
18
|
+
"name": "Chan Meng",
|
|
19
|
+
"url": "https://github.com/ChanMeng666"
|
|
20
|
+
},
|
|
21
|
+
"homepage": "https://ChanMeng666.github.io/a11y-loop/",
|
|
22
|
+
"repository": "https://github.com/ChanMeng666/a11y-loop",
|
|
23
|
+
"license": "MIT",
|
|
24
|
+
"keywords": [
|
|
25
|
+
"accessibility",
|
|
26
|
+
"a11y",
|
|
27
|
+
"wcag",
|
|
28
|
+
"wcag22",
|
|
29
|
+
"axe-core",
|
|
30
|
+
"playwright",
|
|
31
|
+
"plan-mode",
|
|
32
|
+
"agent-skills",
|
|
33
|
+
"aria",
|
|
34
|
+
"contrast",
|
|
35
|
+
"screen-reader",
|
|
36
|
+
"audit"
|
|
37
|
+
]
|
|
38
|
+
}
|
|
39
|
+
]
|
|
40
|
+
}
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
|
|
3
3
|
"name": "a11y-loop",
|
|
4
4
|
"displayName": "a11y-loop",
|
|
5
|
-
"version": "0.2.
|
|
5
|
+
"version": "0.2.1",
|
|
6
6
|
"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.",
|
|
7
7
|
"author": {
|
|
8
8
|
"name": "Chan Meng",
|
|
@@ -21,7 +21,5 @@
|
|
|
21
21
|
"hooks",
|
|
22
22
|
"agent-skills"
|
|
23
23
|
],
|
|
24
|
-
"skills": "./skill/"
|
|
25
|
-
"commands": "./commands/",
|
|
26
|
-
"hooks": "./hooks/hooks.json"
|
|
24
|
+
"skills": "./skill/"
|
|
27
25
|
}
|
package/README.md
CHANGED
|
@@ -383,10 +383,14 @@ Claude-Code-only layer that adds one thing the portable skill cannot do — enfo
|
|
|
383
383
|
plan mode:
|
|
384
384
|
|
|
385
385
|
```bash
|
|
386
|
-
|
|
387
|
-
|
|
386
|
+
claude plugin marketplace add ChanMeng666/a11y-loop
|
|
387
|
+
claude plugin install a11y-loop@chanmeng-a11y-loop
|
|
388
388
|
```
|
|
389
389
|
|
|
390
|
+
Both work as `/plugin marketplace add …` and `/plugin install …` inside Claude Code. From a local
|
|
391
|
+
checkout, `claude plugin marketplace add ./` registers the working copy instead, so the plugin
|
|
392
|
+
tracks your edits.
|
|
393
|
+
|
|
390
394
|
It contributes:
|
|
391
395
|
|
|
392
396
|
- a `PreToolUse` hook matched to `ExitPlanMode`. When a plan changes UI work and says nothing about
|
|
@@ -403,7 +407,7 @@ and a human.
|
|
|
403
407
|
|
|
404
408
|
| | Portable skill | Plugin layer |
|
|
405
409
|
|---|---|---|
|
|
406
|
-
| Install | copy `skill/a11y-loop` |
|
|
410
|
+
| Install | copy `skill/a11y-loop` | `claude plugin install a11y-loop@…` |
|
|
407
411
|
| Works in | 40+ Agent Skills clients | Claude Code only |
|
|
408
412
|
| Gives you | §0 planning, §1 generation, §2 the loop, §3 honest reporting | plan-mode enforcement, `/a11y-plan` |
|
|
409
413
|
| Required? | yes | no |
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "a11y-loop",
|
|
3
|
-
"version": "0.2.
|
|
3
|
+
"version": "0.2.1",
|
|
4
4
|
"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.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|
package/skill/a11y-loop/SKILL.md
CHANGED
|
@@ -28,7 +28,7 @@ compatibility: >-
|
|
|
28
28
|
The generation and honesty rules apply with or without the CLI; every step
|
|
29
29
|
that says "audit" requires it.
|
|
30
30
|
metadata:
|
|
31
|
-
"a11y-loop/version": "0.2.
|
|
31
|
+
"a11y-loop/version": "0.2.1"
|
|
32
32
|
allowed-tools: 'Bash(a11y-loop *) Bash(npx a11y-loop *) Bash(node ${CLAUDE_SKILL_DIR}/../../src/cli.js *)'
|
|
33
33
|
---
|
|
34
34
|
|