ur-agent 1.23.2 → 1.24.0

package/docs/AGENT_FEATURES.md

@@ -64,6 +64,14 @@ ur spec run auth-refactor --all
 ur spec verify auth-refactor
 ```
 
+## v1.24.0 Additions
+
+| Addition | Surface | What it adds |
+| --- | --- | --- |
+| Plugin marketplace capability surfaces | `.ur-plugin/marketplace.json`, `src/utils/plugins/schemas.ts`, `marketplace-plugins/engineering-discipline/` | Marketplace entries can advertise MCP tools, executable skills, templates, validators, language adapters, LSP servers, hooks, agents, and commands. The `engineering-discipline` reference plugin ships a command, reproducible-release skill, release-verifier template, release-gate validator, and Markdown adapter metadata. |
+| Autonomous engineering workflow identity | `README.md`, `documentation/`, `marketplace-plugins/engineering-discipline/skills/reproducible-release` | Positions UR as an autonomous engineering workflow engine: plan, execute, test, verify, document, benchmark, and reproduce, with command evidence and rollback discipline as the product promise. |
+| Release readiness guard | `.github/workflows/test.yml`, `test/releaseReadiness.test.ts` | Asserts production bundle, release, package, and global-install checks run only after the Bun test step succeeds in GitHub CI. |
+
 ## v1.22.3 Additions
 
 | Addition | Surface | What it adds |

package/docs/CODE_FEATURE_INVENTORY.md

@@ -853,10 +853,14 @@ Plugin loading supports:
 - plugin commands
 - plugin agents
 - plugin skills
+- plugin templates
+- plugin validators
 - plugin hooks
 - output styles
 - MCP servers
 - LSP servers
+- language adapters
+- marketplace capability metadata
 - plugin settings
 - duplicate-name handling
 - enable/disable state
@@ -890,6 +894,8 @@ Bundled marketplace plugin families in `marketplace-plugins/**`:
 - PowerPoint deck creation, markdown-to-deck, review, theme, and deck-craft
   skill
 - release notes
+- reproducible release discipline, release-gate validator, release verifier
+  template, and Markdown language-adapter metadata
 - skill forge and skill authoring
 - Word document creation, markdown-to-docx, edit, review, and document-craft
   skill

package/docs/DEVELOPMENT.md

@@ -38,7 +38,8 @@ bun run bundle
 bun run smoke
 bun run secrets:scan
 bun run release:check
-npm pack --dry-run
+bun run package:check
+npm publish --dry-run
 ```
 
 Use `ur test-first detect` when adding a feature to inspect the repository's
@@ -50,7 +51,7 @@ shell commands. Use `ur context-pack scan` when a change adds new manifests,
 command surfaces, or architecture rules that should be captured as project
 context.
 
-The GitHub install path uses the bundled launcher in `dist/cli.js`, so `bun run bundle` must be run before packaging or pushing a release. `bun run release:check` verifies that `package.json`, `bunfig.toml`, the bundle, docs, and `node ./bin/ur.js --version` agree.
+The GitHub install path uses the bundled launcher in `dist/cli.js`, so `bun run bundle` must be run before packaging or pushing a release. `bun run release:check` verifies that `package.json`, `bunfig.toml`, the bundle, docs, and `node ./bin/ur.js --version` agree. The GitHub workflow keeps production bundle, release, package, and global-install checks behind the Bun test step; do not publish, tag, or push release artifacts until that workflow is green.
 
 ## Build
 

package/docs/USAGE.md

@@ -153,7 +153,9 @@ UR includes slash commands and CLI subcommands for common workflows:
 
 - `/help` or `ur --help` for command discovery
 - `ur mcp ...` to configure MCP servers
-- `ur plugin ...` to manage plugins and marketplaces
+- `ur plugin ...` to manage plugins and marketplaces. Marketplace plugins can
+  add MCP tools, commands, executable skills, templates, validators, language
+  adapters, LSP servers, agents, hooks, and output styles.
 - `ur agents` to list configured agents
 - `ur agent-trends` to inspect coverage for current agent technology trends
 - `ur a2a card` to print UR's Agent Card metadata for A2A discovery

package/documentation/app.js

@@ -50,7 +50,7 @@ const featureGroups = [
   {
     title: 'Interoperability',
     tags: ['MCP', 'plugins', 'A2A', 'SDK'],
-    text: 'MCP servers, plugin marketplaces, A2A Agent Card and task server, delegation tokens, and a TypeScript SDK wrapper around headless UR.',
+    text: 'MCP servers, plugin marketplaces for skills, templates, validators, language adapters, A2A Agent Card and task server, delegation tokens, and a TypeScript SDK wrapper around headless UR.',
     commands: ['ur mcp', 'ur plugin', 'ur a2a', 'ur sdk'],
   },
   {
@@ -297,8 +297,8 @@ const commands = [
     name: 'plugin',
     category: 'Interop',
     aliases: ['plugins'],
-    summary: 'Manage UR plugins and plugin marketplaces.',
-    examples: ['ur plugin list', 'ur plugin install hello@ur-plugins-official', 'ur plugin update <plugin>', 'ur plugin disable <plugin>'],
+    summary: 'Manage UR plugins and marketplaces for MCP tools, skills, templates, validators, and language adapters.',
+    examples: ['ur plugin list', 'ur plugin install hello@ur-plugins-official', 'ur plugin install engineering-discipline@ur-plugins-official', 'ur plugin update <plugin>', 'ur plugin disable <plugin>'],
   },
   {
     name: 'repo-edit',

package/documentation/index.html

@@ -43,7 +43,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.22.3</p>
+          <p class="eyebrow">Version 1.24.0</p>
           <h1>UR Agent Documentation</h1>
           <p class="lead">A practical, tutorial-style reference for installing, configuring, automating, extending, and operating UR Agent.</p>
         </div>
@@ -56,8 +56,8 @@
       <section id="overview" class="section">
         <div class="section-heading">
           <p class="eyebrow">What UR Is</p>
-          <h2>Terminal coding agent with local-first model routing</h2>
-          <p>UR runs from the terminal, uses the local Ollama app for model calls, and combines project context, tools, MCP, plugins, skills, workflows, automations, and agent orchestration into one CLI.</p>
+          <h2>Autonomous engineering workflow engine</h2>
+          <p>UR is not only chat, autocomplete, or code edits. It turns work into a plan, executes patches, tests and verifies them, documents the result, benchmarks behavior, and keeps the run reproducible from the terminal.</p>
         </div>
         <div class="stat-grid">
           <article>
@@ -72,6 +72,10 @@
             <strong>Agent platform</strong>
             <span>Workflows, patterns, crews, goals, evals, memory, knowledge, A2A, provenance, and templates are first-class commands.</span>
           </article>
+          <article>
+            <strong>Plugin marketplace</strong>
+            <span>Plugins can add MCP tools, skills, templates, validators, language adapters, LSP servers, agents, hooks, and output styles.</span>
+          </article>
           <article>
             <strong>Reliable repo editing</strong>
             <span><code>ur repo-edit</code> indexes files and symbols, plans AST-aware renames, previews patches, and rolls back failed multi-file applies.</span>
@@ -86,7 +90,7 @@
           </article>
           <article>
             <strong>Release checks</strong>
-            <span>Typecheck, tests, bundle verification, smoke, package checks, and secret scan are part of the release path.</span>
+            <span>Typecheck, tests, bundle verification, smoke, package checks, secret scan, and dry-run publish are part of the release path.</span>
           </article>
         </div>
       </section>
@@ -442,7 +446,7 @@ UR_VERIFIER_AUTO_SUBAGENT=1</code></pre>
 ur mcp add-json local-tools '{"command":"node","args":["server.js"]}'
 ur plugin list
 ur plugin install &lt;plugin&gt;</code></pre>
-            <p>MCP servers and plugins expand tool access. Treat them as trusted code.</p>
+            <p>MCP servers and marketplace plugins expand tools, executable skills, templates, validators, language adapters, and review workflows. Treat them as trusted code.</p>
           </article>
         </div>
       </section>

package/marketplace-plugins/README.md

@@ -0,0 +1,69 @@
+# marketplace-plugins/
+
+First-party plugins for the **ur-plugins-official** marketplace.
+
+Each subdirectory here is a self-contained plugin. The marketplace
+manifest at `.ur-plugin/marketplace.json` (at the repo root) lists which of
+them are published.
+
+## Shipped plugins
+
+| Plugin | Slash command | What it does |
+| --- | --- | --- |
+| [`hello`](./hello) | `/hello [name]` | Example greeting. Use as a template. |
+| [`git-summary`](./git-summary) | `/git-summary` | One-paragraph factual summary of the working tree and recent commits. |
+| [`code-review`](./code-review) | `/code-review [base-ref]` | Structured review of the working diff. Correctness, style, test coverage, security, TL;DR verdict. |
+| [`explain-error`](./explain-error) | `/explain-error [command]` | Re-runs a failing command and decodes the error in plain English with two next steps. |
+| [`release-notes`](./release-notes) | `/release-notes [since-ref]` | Drafts release notes grouped by Features / Fixes / Documentation / Other since the last tag. |
+| [`evaluate-response`](./evaluate-response) | `/evaluate-response` | Adversarial self-evaluation of the most recent assistant turn. |
+| [`obsidian`](./obsidian) | `/second-brain` (+4) | Operate an Obsidian vault as a second brain — atomic notes, daily notes, MOCs, backlinks, cited search. Direct file edits or the Local REST API MCP server. |
+| [`github`](./github) | `/gh-pr-review` (+3) | Review and open pull requests, triage issues, check repo health — via the official GitHub MCP server or the `gh` CLI. |
+| [`gitlab`](./gitlab) | `/gl-mr-review` (+3) | Review and open merge requests, triage issues, watch CI/CD pipelines — via the official GitLab MCP server or the `glab` CLI. |
+| [`huggingface`](./huggingface) | `/hf-model-search` (+3) | Search, vet, and download Hub models and datasets — via the official Hugging Face MCP server or the `hf` CLI. |
+| [`word`](./word) | `/docx-new` (+3) | Create, convert, review, and edit Word documents — via the Office Word MCP server or a pandoc / python-docx fallback. |
+| [`powerpoint`](./powerpoint) | `/pptx-new` (+3) | Build, convert, review, and theme PowerPoint decks — via the Office PowerPoint MCP server or a python-pptx fallback. |
+| [`miro`](./miro) | `/miro-board` (+3) | Create boards, diagrams, and sticky clusters and summarize boards — via Miro's official MCP server or the REST API. |
+| [`skill-forge`](./skill-forge) | `/forge-skill` (+1) | The active model authors a complete `SKILL.md` from your description and saves it to your skills directory. |
+| [`engineering-discipline`](./engineering-discipline) | `/discipline-check` | Reference plugin that ships a command, executable skill, agent template, validator, and Markdown language adapter metadata. |
+
+Seven of these are **integration plugins**: each bundles an official MCP server,
+several slash commands, and a methodology skill, and prompts for its config
+(tokens, vault path, output folders) on enable. The Office plugins run their MCP
+server through `uvx` (install `uv`) and fall back to local Python libraries.
+Secrets are stored in secure storage, never in plaintext settings.
+
+[`skill-forge`](./skill-forge) is a **meta plugin** (no MCP): its commands run as
+prompts, so the active session model authors and saves the skill for you.
+
+[`engineering-discipline`](./engineering-discipline) is a **marketplace
+capability reference plugin**. It demonstrates every standard extension surface
+UR accepts from marketplace plugins: commands, executable skills, reusable agent
+templates, deterministic validators, language adapters, and LSP server metadata.
+
+## Adding a new plugin
+
+1. Copy `hello/` to a new directory, e.g. `marketplace-plugins/my-plugin/`.
+2. Edit `my-plugin/.ur-plugin/plugin.json` with the plugin's real metadata.
+3. Replace the example command in `my-plugin/commands/` with your own.
+4. Add optional extension folders as needed:
+   - `skills/<name>/SKILL.md`
+   - `templates/<name>.md`
+   - `validators/<name>.json`
+   - `mcpServers` or `lspServers` in `.ur-plugin/plugin.json`
+   - `languageAdapters` in `.ur-plugin/plugin.json`
+5. Add an entry to `.ur-plugin/marketplace.json` (sibling to existing
+   entries).
+6. Set the entry's `capabilities` array so users can see whether it adds MCP
+   tools, skills, templates, validators, language adapters, LSP servers,
+   commands, agents, or hooks before installation.
+7. Open a PR against `Maitham16/UR-mapek`.
+
+See [`hello/README.md`](./hello/README.md) for the smallest possible example.
+
+## Schemas
+
+The shapes for `marketplace.json` and `plugin.json` are defined in the
+agent source — see `src/utils/plugins/schemas.ts` (`PluginMarketplaceSchema`
+and `PluginManifestSchema`). The schemas are strict-by-default but
+unknown fields on marketplace entries are silently stripped so future
+versions stay forward-compatible.

package/marketplace-plugins/code-review/.ur-plugin/plugin.json

@@ -0,0 +1,13 @@
+{
+  "name": "code-review",
+  "version": "0.1.0",
+  "description": "Adds /code-review — structured review of the working diff against a base ref.",
+  "author": {
+    "name": "Maitham Al-rubaye",
+    "url": "https://github.com/Maitham16/ur-agent"
+  },
+  "homepage": "https://github.com/Maitham16/ur-agent/tree/master/marketplace-plugins/code-review",
+  "repository": "https://github.com/Maitham16/ur-agent",
+  "license": "LicenseRef-UR-Agent-Non-Commercial-Self-Responsibility",
+  "keywords": ["code-review", "git", "diff", "quality"]
+}

package/marketplace-plugins/code-review/README.md

@@ -0,0 +1,37 @@
+# code-review
+
+Adds `/code-review` — a structured review of the working diff against a
+base ref.
+
+## Use
+
+```text
+/code-review
+/code-review main
+/code-review v1.2.0
+```
+
+If no base ref is given, the plugin tries `main`, then `master`, then
+`HEAD~5`.
+
+## What it does
+
+Runs `git diff <base>...HEAD`, then asks the model for a markdown report
+with four sections (Correctness, Style, Test coverage, Security) and a
+mandatory one-line TL;DR (`Looks good` / `Has nits` / `Has blockers`).
+
+Sections with no findings are omitted, not padded.
+
+## Install
+
+```text
+/plugin install code-review@ur-plugins-official
+```
+
+## Pair with the verifier
+
+`/code-review` is a *static* read of the diff. The verifier subagent
+(`/verify` or auto on every "done") is a *dynamic* check — it actually
+runs builds, tests, and lints. They're complementary: code-review catches
+things the verifier can't (style, subtle logic), and the verifier catches
+things code-review can't (does it actually compile and pass tests).

package/marketplace-plugins/code-review/commands/code-review.md

@@ -0,0 +1,47 @@
+---
+description: Review the working diff against a base ref. Returns a structured report.
+argument-hint: "[base-ref] (default: main)"
+---
+
+Determine the base ref: if `$ARGUMENTS` is non-empty, use it; otherwise use
+`main` if it exists, otherwise `master`, otherwise `HEAD~5`.
+
+Run the diff:
+
+```sh
+git diff <base>...HEAD
+```
+
+If the diff is empty, say "No changes to review against `<base>`." and stop.
+
+Otherwise produce a markdown report with these sections, in order. Skip any
+section that has no findings rather than padding it.
+
+### Correctness
+Logic errors, missed edge cases, null / empty / boundary handling, off-by-one,
+concurrency bugs, error paths that don't propagate. For each, name the file
+and line and quote the problematic snippet.
+
+### Style and consistency
+Inconsistent naming with the rest of the file, dead or unreachable code,
+duplicated logic, abstraction that obscures rather than clarifies, comments
+that contradict the code.
+
+### Test coverage
+Was test-shaped code touched? Are there tests for the new behaviour? Flag
+any change to public surface area with no matching test change.
+
+### Security
+Injection risks (SQL, shell, path), secret / token leakage in logs or
+errors, unsafe deserialization, missing input validation at trust
+boundaries, permissive permission grants.
+
+### TL;DR
+End with one line, exactly one of:
+
+- `TL;DR: Looks good.` — no findings or only nits, nothing blocking.
+- `TL;DR: Has nits.` — one or more cosmetic findings, nothing blocking.
+- `TL;DR: Has blockers.` — at least one correctness or security finding
+  that should be fixed before merging.
+
+Do not editorialize about the author. Review the code, not the person.

package/marketplace-plugins/engineering-discipline/.ur-plugin/plugin.json

@@ -0,0 +1,33 @@
+{
+  "name": "engineering-discipline",
+  "version": "0.1.0",
+  "description": "Reference plugin for UR's marketplace extensibility: a CI/release command, executable skill, agent template, verifier validator, and language/LSP adapter metadata.",
+  "author": {
+    "name": "Maitham Al-rubaye",
+    "url": "https://github.com/Maitham16/ur-agent"
+  },
+  "homepage": "https://github.com/Maitham16/ur-agent/tree/master/marketplace-plugins/engineering-discipline",
+  "repository": "https://github.com/Maitham16/ur-agent",
+  "license": "LicenseRef-UR-Agent-Non-Commercial-Self-Responsibility",
+  "keywords": ["workflow", "ci", "release", "validator", "template", "language-adapter"],
+  "skills": "./skills",
+  "templates": "./templates",
+  "validators": "./validators",
+  "languageAdapters": {
+    "markdown": {
+      "extensions": [".md", ".mdx"],
+      "engine": "lsp",
+      "lspServerName": "markdown"
+    }
+  },
+  "lspServers": {
+    "markdown": {
+      "command": "markdown-language-server",
+      "args": ["--stdio"],
+      "extensionToLanguage": {
+        ".md": "markdown",
+        ".mdx": "markdown"
+      }
+    }
+  }
+}

package/marketplace-plugins/engineering-discipline/README.md

@@ -0,0 +1,21 @@
+# engineering-discipline
+
+Reference plugin for UR's marketplace extensibility.
+
+It demonstrates how a marketplace plugin can add more than a slash command:
+
+- command: `/discipline-check`
+- skill: `engineering-discipline:reproducible-release`
+- agent template: `release-verifier`
+- validator: `release-gate`
+- language adapter: Markdown/MDX through an LSP declaration
+
+## Install
+
+```sh
+/plugin install engineering-discipline@ur-plugins-official
+```
+
+The validator is intentionally conservative and mirrors the release gate used
+for production readiness. The language adapter only activates when the matching
+Markdown language server is installed locally.

package/marketplace-plugins/engineering-discipline/commands/discipline-check.md

@@ -0,0 +1,25 @@
+---
+description: "Check whether a change is ready for reproducible release: plan, patch, tests, verifier evidence, docs, benchmark notes, and rollback path."
+argument-hint: "[changed area or release target]"
+allowed-tools:
+  - "Bash(git status:*)"
+  - "Bash(git diff:*)"
+  - "Bash(bun run typecheck:*)"
+  - "Bash(bun run lint:*)"
+  - "Bash(bun test:*)"
+  - "Bash(bun run release:check:*)"
+---
+
+Audit the current change as a reproducible engineering workflow.
+
+Check whether the work has a clear plan, scoped patch, executed tests, verifier
+evidence, documentation updates, benchmark or eval notes when relevant, and a
+rollback path. Prefer command evidence over claims. Do not mark the change ready
+unless the required commands were actually executed and passed.
+
+Return:
+
+1. Status: READY, BLOCKED, or NEEDS-EVIDENCE.
+2. Evidence commands observed.
+3. Missing evidence.
+4. Release or rollback risk.

package/marketplace-plugins/engineering-discipline/skills/reproducible-release/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: Reproducible Release
+description: Use when preparing a UR-style engineering change for release. Enforces spec -> plan -> patch -> test -> verify -> document -> benchmark -> reproduce, with explicit command evidence and rollback notes.
+version: 0.1.0
+---
+
+# Reproducible Release
+
+Use this skill when a change must be ready for production, npm packaging, or a
+research/demo artifact.
+
+## Workflow
+
+1. State the intended release surface and affected commands.
+2. Inspect the diff and list public API, generated-file, and safety risks.
+3. Run the smallest relevant compile/test/lint checks, then broaden to the full
+   release gate when risk warrants it.
+4. Record command evidence exactly: command, exit code, stdout/stderr summary,
+   and next action.
+5. Confirm documentation and marketplace files are updated when user-facing
+   behavior changes.
+6. Produce a PR-style report with summary, changed files, tests run, risks,
+   rollback command, and remaining TODOs.
+
+## Hard Rules
+
+- Never claim tests passed without command evidence.
+- Never hide a failed command or skipped gate.
+- Never edit generated/vendor files unless the task explicitly requires it.
+- Never publish or tag until the release gate passes and the user explicitly
+  asks for publishing.

package/marketplace-plugins/engineering-discipline/templates/release-verifier.md

@@ -0,0 +1,18 @@
+---
+name: release-verifier
+description: Reviews whether a change is releasable, auditable, and rollback-ready.
+color: green
+effort: high
+permissionMode: default
+memory: project
+---
+
+You are a release verification agent.
+
+Review the current change as if it were going to production. Demand command
+evidence for compile, lint, tests, bundle, smoke, package, and secret scan when
+the change touches release or runtime behavior. Inspect docs and generated
+artifacts. Report findings first, then summarize the release readiness state.
+
+Do not approve a release if the production bundle is stale, tests were not run,
+or publishing would not be gated by successful CI.

package/marketplace-plugins/engineering-discipline/validators/release-gate.json

@@ -0,0 +1,7 @@
+{
+  "name": "release-gate",
+  "command": "bun run typecheck && bun run lint && bun test && bun run release:check",
+  "when": "always",
+  "patterns": ["src/**", "test/**", "package.json", "bunfig.toml", "docs/**", "README.md"],
+  "timeoutMs": 120000
+}

package/marketplace-plugins/evaluate-response/.ur-plugin/plugin.json

@@ -0,0 +1,13 @@
+{
+  "name": "evaluate-response",
+  "version": "0.1.0",
+  "description": "Adds /evaluate-response — adversarial self-evaluation of the most recent assistant turn.",
+  "author": {
+    "name": "Maitham Al-rubaye",
+    "url": "https://github.com/Maitham16/ur-agent"
+  },
+  "homepage": "https://github.com/Maitham16/ur-agent/tree/master/marketplace-plugins/evaluate-response",
+  "repository": "https://github.com/Maitham16/ur-agent",
+  "license": "LicenseRef-UR-Agent-Non-Commercial-Self-Responsibility",
+  "keywords": ["quality", "self-evaluation", "verifier"]
+}

package/marketplace-plugins/evaluate-response/README.md

@@ -0,0 +1,42 @@
+# evaluate-response
+
+Adds `/evaluate-response` — adversarial self-evaluation of the most recent
+assistant response.
+
+## Use
+
+```text
+/evaluate-response
+```
+
+Invoke right after the agent finishes a task to catch hallucinated
+completions, missed sub-questions, factual drift, or narrated-but-not-done
+work.
+
+## What it returns
+
+A markdown report against five criteria — Completeness, Accuracy, Tool
+use vs narration, Honesty about completion, Clarity — plus a mandatory
+one-line verdict:
+
+```
+QUALITY: HIGH | MEDIUM | LOW — <rationale>
+```
+
+And one concrete, specific improvement (not generic advice).
+
+## How it pairs with the verifier
+
+The verifier subsystem catches structural problems automatically (no Write
+call but claimed "created the file", same Bash call 3 times in a row, the
+build doesn't compile). `/evaluate-response` is for the harder cases the
+verifier can't see: did the response actually answer the question, were the
+facts right, was the tone honest.
+
+Useful as a manual cross-check before committing what the agent produced.
+
+## Install
+
+```text
+/plugin install evaluate-response@ur-plugins-official
+```

package/marketplace-plugins/evaluate-response/commands/evaluate-response.md

@@ -0,0 +1,61 @@
+---
+description: Adversarially evaluate the most recent assistant response. Be ruthless.
+---
+
+You are about to evaluate your own most recent response — the assistant
+message immediately before this command was invoked. Your goal is to catch
+your own mistakes, not to defend your own work.
+
+Look at the most recent assistant turn in the transcript. Read both the
+text and the tool calls. Then evaluate it against these criteria. Be
+specific. "Looks fine" is not an answer.
+
+### Completeness
+
+Did the response actually answer every part of the user's question? List
+any sub-question or sub-task that was skipped, glossed over, or deferred
+without explicit acknowledgement.
+
+### Accuracy
+
+Are factual claims and code references correct? Spot-check at least one
+file path or symbol name the response mentioned by reading it with the
+Read tool. Report any drift.
+
+### Tool use vs narration
+
+Did the response use tools where appropriate, or did it narrate work it
+should have actually performed? A response that says "I would edit X to
+do Y" without calling Edit is a tool-use failure. Flag specifically.
+
+### Honesty about completion
+
+Did the response claim work that was not actually performed? Cross-check
+"I created / edited / ran X" claims against actual tool calls in the same
+turn. If a claim has no matching successful tool result, that is a
+hallucinated completion — call it out.
+
+### Clarity and concision
+
+Was the response well structured for the user to skim? Or did it bury the
+useful information under filler? One sentence each on structure and length.
+
+### Verdict
+
+End with exactly one line in this format:
+
+```
+QUALITY: HIGH | MEDIUM | LOW — <one-sentence rationale>
+```
+
+- **HIGH**: complete, accurate, honest, used tools where needed, easy to
+  read. No criterion failed.
+- **MEDIUM**: one or two minor issues. Useful but not great.
+- **LOW**: a criterion failed in a way that would mislead the user
+  (hallucinated completion, factually wrong claim, missed a question).
+
+Then list one specific, concrete improvement the response could have made.
+Not generic advice — a precise sentence the response should have included
+or a tool call it should have made.
+
+Do not soften findings. The point of this command is signal, not comfort.

package/marketplace-plugins/explain-error/.ur-plugin/plugin.json

@@ -0,0 +1,13 @@
+{
+  "name": "explain-error",
+  "version": "0.1.0",
+  "description": "Adds /explain-error — re-runs a failing command and diagnoses the error in plain English.",
+  "author": {
+    "name": "Maitham Al-rubaye",
+    "url": "https://github.com/Maitham16/ur-agent"
+  },
+  "homepage": "https://github.com/Maitham16/ur-agent/tree/master/marketplace-plugins/explain-error",
+  "repository": "https://github.com/Maitham16/ur-agent",
+  "license": "LicenseRef-UR-Agent-Non-Commercial-Self-Responsibility",
+  "keywords": ["debug", "error", "troubleshooting"]
+}

package/marketplace-plugins/explain-error/README.md

@@ -0,0 +1,32 @@
+# explain-error
+
+Adds `/explain-error` — diagnose a failing command, in plain English, with
+two concrete next steps to try.
+
+## Use
+
+```text
+/explain-error bun test
+/explain-error
+```
+
+With a command argument, re-runs that command and analyzes the failure.
+Without an argument, looks back through the transcript for the most recent
+failing Bash call.
+
+## What it returns
+
+Three short sections:
+
+- **What the error means** — plain-English decoding of the message.
+- **Most likely cause** — the single most plausible root cause given the
+  project context.
+- **Next steps** — two concrete things to try, ordered by likelihood.
+
+Stays specific to the error in front of it. Does not lecture about debugging.
+
+## Install
+
+```text
+/plugin install explain-error@ur-plugins-official
+```