Accept cross-agent install updates

.claude-plugin/marketplace.json

@@ -0,0 +1,18 @@
+{
+  "$schema": "https://json.schemastore.org/claude-code-marketplace-manifest.json",
+  "name": "humanizer",
+  "owner": {
+    "name": "blader",
+    "url": "https://github.com/blader"
+  },
+  "description": "The humanizer skill, installable as a Claude Code plugin.",
+  "plugins": [
+    {
+      "name": "humanizer",
+      "source": "./",
+      "description": "Remove signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's \"Signs of AI writing\" guide.",
+      "license": "MIT",
+      "keywords": ["writing", "editing", "ai-detection", "humanize", "prose", "style"]
+    }
+  ]
+}

.claude-plugin/plugin.json

@@ -0,0 +1,14 @@
+{
+  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
+  "name": "humanizer",
+  "description": "Remove signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's \"Signs of AI writing\" guide.",
+  "version": "2.8.1",
+  "author": {
+    "name": "blader",
+    "url": "https://github.com/blader"
+  },
+  "homepage": "https://github.com/blader/humanizer",
+  "repository": "https://github.com/blader/humanizer",
+  "license": "MIT",
+  "keywords": ["writing", "editing", "ai-detection", "humanize", "prose", "style"]
+}

AGENTS.md

@@ -4,19 +4,22 @@ Guidance for AI coding agents (Claude Code, Codex, Warp, etc.) working in this r
 
 ## What this repo is
 
-A **Claude Code / OpenCode skill** implemented entirely as Markdown. The runtime artifact is `SKILL.md`: the agent reads its YAML frontmatter (metadata + allowed tools) followed by the editor prompt. There is no build step and no code to run.
+A portable agent skill implemented entirely as Markdown. The runtime artifact is `SKILL.md`: the agent reads its YAML frontmatter (metadata + allowed tools) followed by the editor prompt. There is no build step and no code to run, and the repo should avoid wording that limits support to one or two harnesses.
 
 ## Key files
 
-- `SKILL.md` — the skill itself. YAML frontmatter (`name`, `version`, `description`, `allowed-tools`) followed by the canonical, numbered pattern list with before/after examples. **This is the source of truth.**
+- `SKILL.md` — the skill itself. YAML frontmatter (`name`, `version`, `description`, `compatibility`, `allowed-tools`) followed by the canonical, numbered pattern list with before/after examples. **This is the source of truth.**
 - `README.md` — for humans: installation, usage, a summary table of the patterns, and a version history.
+- `.claude-plugin/plugin.json` — optional Claude Code plugin manifest.
+- `.claude-plugin/marketplace.json` — optional single-repo marketplace entry so `/plugin marketplace add blader/humanizer` works.
 
 ## The maintenance contract
 
 `SKILL.md` and `README.md` must stay in sync. When you change behavior or content:
 
 - **Patterns:** the skill currently defines **33 numbered patterns**. If you add, remove, or renumber any, update the README pattern table, its "N Patterns Detected" heading, and every cross-reference in the same change. Keep numbering stable unless you are deliberately renumbering.
-- **Version:** `SKILL.md` frontmatter has a `version:` field and `README.md` has a "Version History" section. Bump both together.
+- **Version:** `SKILL.md` frontmatter has a `version:` field, `README.md` has a "Version History" section, and `.claude-plugin/plugin.json` has a `version` field. Bump them together so package metadata matches the skill. (`marketplace.json` intentionally omits a version so `plugin.json` stays the package source of truth.)
+- **Compatibility:** keep install and usage language harness-neutral. The skill should work in any agent harness that can load Markdown skill instructions; Claude Code, OpenCode, Codex, and other harnesses are examples, not limits.
 - **Non-obvious fixes:** if you change the prompt to handle a tricky failure mode (a repeated mis-edit, an unexpected tone shift), add a short note to the README version history explaining what was fixed and why.
 
 ## Editing SKILL.md

README.md

@@ -1,54 +1,66 @@
 # Humanizer
 
-A skill for Claude Code and OpenCode that removes signs of AI-generated writing from text, making it sound more natural and human.
+A portable agent skill that removes signs of AI-generated writing from text, making it sound more natural and human. It is plain Markdown, so it can run in any harness that supports skill-style instructions.
 
 ## Installation
 
-### Claude Code
+### Skills CLI
 
-Clone directly into Claude Code's skills directory:
+Install with the cross-agent skills CLI:
 
 ```bash
-mkdir -p ~/.claude/skills
-git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer
+npx skills add blader/humanizer
 ```
 
-Or copy the skill file manually if you already have this repo cloned:
+Update an existing install:
 
 ```bash
-mkdir -p ~/.claude/skills/humanizer
-cp SKILL.md ~/.claude/skills/humanizer/
+npx skills update humanizer
 ```
 
-### OpenCode
-
-Clone directly into OpenCode's skills directory:
+To install into every supported agent harness:
 
 ```bash
-mkdir -p ~/.config/opencode/skills
-git clone https://github.com/blader/humanizer.git ~/.config/opencode/skills/humanizer
+npx skills add blader/humanizer --agent '*'
 ```
 
-Or copy the skill file manually if you already have this repo cloned:
+To target one configured harness, pass its agent name:
 
 ```bash
-mkdir -p ~/.config/opencode/skills/humanizer
-cp SKILL.md ~/.config/opencode/skills/humanizer/
+npx skills add blader/humanizer --agent <agent-name>
 ```
 
-> **Note:** OpenCode also scans `~/.claude/skills/` for compatibility, so if you use both tools, a single clone into `~/.claude/skills/humanizer/` is enough.
+### Claude Code plugin
 
-## Usage
+Claude Code users can also install Humanizer as a plugin:
+
+```
+/plugin marketplace add blader/humanizer
+/plugin install humanizer@humanizer
+```
+
+The skill is then invoked as `/humanizer:humanizer`.
+
+### Manual
+
+Any agent harness can use the skill directly because the runtime artifact is `SKILL.md`. Install it wherever your harness expects skill directories, or copy `SKILL.md` into an existing skill folder.
 
-### Claude Code
+For example:
 
+```bash
+git clone https://github.com/blader/humanizer.git /path/to/your/skills/humanizer
 ```
-/humanizer
 
-[paste your text here]
+Or, if you already have this repo cloned:
+
+```bash
+mkdir -p /path/to/your/skills/humanizer
+cp SKILL.md /path/to/your/skills/humanizer/
 ```
 
-### OpenCode
+## Usage
+
+Invoke the skill however your agent harness exposes installed skills. Common forms include a slash command or a direct request:
 
 ```
 /humanizer
@@ -56,8 +68,6 @@ cp SKILL.md ~/.config/opencode/skills/humanizer/
 [paste your text here]
 ```
 
-Or ask the model to humanize text directly in either tool:
-
 ```
 Please humanize this text: [your text]
 ```
@@ -183,6 +193,7 @@ The skill also includes a final "obviously AI generated" audit pass and a second
 
 ## Version History
 
+- **2.8.1** - Added cross-agent installation docs, optional Claude Code plugin packaging, and a compact secondhand-text false-positive guard. No change to the 33 patterns.
 - **2.8.0** - Added style/cadence patterns #31-33 for manufactured punchlines, aphorism formulas, and conversational rhetorical openers; expanded #20 to catch offer-to-continue chatbot closers. 33 patterns total.
 - **2.7.0** - Added pattern #30 (diff-anchored writing); made em/en dashes a hard cut rather than "overuse"; expanded #21 to cover speculative gap-filling ("maintains a low profile"). 30 patterns total.
 - **2.6.0** - Cleanup pass: consolidated the duplicated workflow sections, gated the personality guidance to content where voice is wanted, removed the model-fingerprinting subsection, and condensed the worked example. No change to the 29 patterns.

SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: humanizer
-version: 2.8.0
+version: 2.8.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -9,7 +9,7 @@ description: |
   attributions, em dash overuse, rule of three, AI vocabulary words, passive
   voice, negative parallelisms, and filler phrases.
 license: MIT
-compatibility: claude-code opencode
+compatibility: any-agent
 allowed-tools:
   - Read
   - Write
@@ -538,6 +538,7 @@ A clean human writer can hit several of the patterns above without any AI involv
 - **"Honestly" or "look" mid-sentence.** These are ordinary in casual writing. The tell is the standalone theatrical opener, not the word itself.
 - **Unsourced claims.** Most of the web is unsourced. Lack of citations doesn't prove anything.
 - **Correct, complex formatting.** Visual editors and templates produce clean output without any AI.
+- **Secondhand text.** Do not rewrite watched phrases inside quotations, titles, proper names, or examples where the phrase is being discussed rather than used.
 
 When in doubt, look for **clusters** of tells, not isolated ones. A single em dash means nothing; em dashes plus rule-of-three plus *vibrant tapestry* plus a "Conclusion" section is a confession.