@diegopetrucci/pi-extensions 0.1.50 → 0.1.52

package/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/README.md

@@ -1,5 +1,7 @@
 # pi-extensions
 
+[![Total npm downloads](https://img.shields.io/npm/dt/%40diegopetrucci%2Fpi-extensions?label=total%20npm%20downloads)](https://www.npmjs.com/package/@diegopetrucci/pi-extensions)
+
 A collection of [pi](https://github.com/earendil-works/pi-mono) agent extensions and skills I made.
 
 - [`agent-workflow-audit`](./extensions/agent-workflow-audit): Adds `/agent-workflow-audit`, which runs an isolated repo workflow audit subagent and returns only the final distilled report to the main session.
@@ -8,15 +10,16 @@ A collection of [pi](https://github.com/earendil-works/pi-mono) agent extensions
 - [`brrr`](./extensions/brrr): Sends brrr push notifications when pi finishes an agent turn and is ready for input, with optional macOS idle gating.
 - [`claude-fast`](./extensions/claude-fast): Adds `/claude-fast` to enable Anthropic Claude Fast mode for supported Claude Opus models by injecting `speed: "fast"`.
 - [`confirm-destructive`](./extensions/confirm-destructive): Confirms before destructive session actions like clear, switch, and fork.
+- [`contrarian`](./extensions/contrarian): Adds a read-only contrarian tool that spins up an isolated subprocess to stress-test plans, designs, assumptions, bug hypotheses, and conclusions by steelmanning the strongest opposing case.
 - [`context-cap`](./extensions/context-cap): Caps effective model context windows at 200k tokens by default so pi avoids the `dumb zone`; toggle temporarily with `/context-cap`.
 - [`context-inspector`](./extensions/context-inspector): Adds `/context`, a local self-contained HTML dashboard that breaks down where the current session context is going, with category overview, top offenders, and drilldown search.
 - [`dirty-repo-guard`](./extensions/dirty-repo-guard): Prompts before new sessions, session switches, or forks when the current git repo has uncommitted changes.
 - [`git-footer`](./extensions/git-footer): Standalone extension that adds TLH-style git dirty counts, ahead/behind, and optional PR number to pi's built-in footer status area.
 - [`gnosis`](./extensions/gnosis): Exposes the `gn` repo-local knowledge base CLI as an agent tool for searching and recording durable project decisions, constraints, and intent.
-- [`inline-bash`](./extensions/inline-bash): Expands `!{command}` snippets in user prompts by running them through bash before the prompt reaches the agent.
 - [`illustrations-to-explain-things`](./extensions/illustrations-to-explain-things): Adds a skill for generating clean, absurd Xiaohei-style article illustrations, shot lists, image edits, and visual metaphors.
+- [`inline-bash`](./extensions/inline-bash): Expands `!{command}` snippets in user prompts by running them through bash before the prompt reaches the agent.
 - [`librarian`](./extensions/librarian): Adds a GitHub research scout with a local repo checkout cache disabled by default under the OS user cache directory, toggleable with `/librarian-cache`, configurable subagent model/thinking defaults via `/librarian-config`, and cached repos expiring after 7 days of non-use.
-- [`minimal-footer`](./extensions/minimal-footer): Replaces pi's built-in footer with a minimal configurable two-line layout: branch/repo on the first line, context/model on the second, optional `DUMB ZONE`, optional `xp` marker, plus OpenAI Codex 5-hour and 7-day usage when available.
+- [`minimal-footer`](./extensions/minimal-footer): Replaces pi's built-in footer with a minimal configurable two-line layout: branch plus cached git dirty/ahead/PR status and repo on the first line, context/model on the second, optional `DUMB ZONE`, optional `xp` marker, plus OpenAI Codex 5-hour and 7-day usage when available.
 - [`notify`](./extensions/notify): Sends configurable terminal, desktop, bell, and sound notifications when pi finishes and is ready for input.
 - [`openai-fast`](./extensions/openai-fast): Adds `/fast` to enable OpenAI Codex Fast mode for ChatGPT-auth GPT-5.4 and GPT-5.5 by injecting the priority service tier.
 - [`oracle`](./extensions/oracle): Adds an Amp-style read-only oracle tool that auto-selects the strongest reasoning model on the current provider/subscription, supports persisted `/oracle` model/thinking defaults, requests xhigh reasoning by default and clamps to model capabilities, and shows live status while running.

package/extensions/agent-workflow-audit/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/agent-workflow-audit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-agent-workflow-audit",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "A pi extension that runs an isolated repo workflow audit and returns only the final report to the main session.",
   "keywords": [
     "pi-package",

package/extensions/annotate-git-diff/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/annotate-git-diff/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-annotate-git-diff",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "A standalone pi extension that adds /annotate-git-diff, a native Glimpse UI for annotating git diffs and sending feedback to the editor.",
   "keywords": [
     "pi-package",

package/extensions/annotate-last-message/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/annotate-last-message/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-annotate-last-message",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "A standalone pi extension that adds /annotate-last-message, a native Glimpse UI for annotating the latest assistant reply.",
   "keywords": [
     "pi-package",

package/extensions/brrr/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/brrr/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-brrr",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "A pi extension that sends brrr push notifications when pi is ready for input.",
   "keywords": [
     "pi-package",

package/extensions/claude-fast/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/claude-fast/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-claude-fast",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "A pi extension that enables Anthropic Claude Fast mode for supported Claude Opus models by injecting speed=fast.",
   "keywords": [
     "pi-package",

package/extensions/confirm-destructive/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/confirm-destructive/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-confirm-destructive",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "A pi extension that confirms destructive session actions.",
   "keywords": [
     "pi-package",

package/extensions/context-cap/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/context-cap/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-context-cap",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "A pi extension that caps effective model context windows at 200k tokens for earlier auto-compaction.",
   "keywords": [
     "pi-package",

package/extensions/context-inspector/.pi-fleet-tested-version

@@ -1 +1 @@
-0.78.0
+0.79.10

package/extensions/context-inspector/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@diegopetrucci/pi-context-inspector",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "A pi extension that opens a local HTML dashboard explaining where the current session context is going.",
   "keywords": [
     "pi-package",

package/extensions/contrarian/.pi-fleet-tested-version

@@ -0,0 +1 @@
+0.79.10

package/extensions/contrarian/README.md

@@ -0,0 +1,85 @@
+# contrarian
+
+A read-only contrarian subagent for [pi](https://github.com/earendil-works/pi-mono).
+
+It adds a `contrarian` tool that spins up a separate pi subprocess to stress-test plans, designs, assumptions, bug hypotheses, review conclusions, and product directions by steelmanning the strongest credible opposing case.
+
+This is adapted from the TLH [`contrarian` subagent prompt](https://github.com/diegopetrucci/the-last-harness/blob/main/agents/subagents/contrarian.md) into a standalone pi extension.
+
+## What it does
+
+- creates an isolated read-only subprocess
+- prefers a strong model on the opposite model family/provider when available, then falls back to the best available model
+- requests `high` reasoning by default for reasoning models, then clamps to the model-supported thinking level
+- defaults to `read,grep,find,ls`, with optional non-mutating bash inspection
+- renders the contrarian response with model, thinking level, timing, and usage info
+- shows a live contrarian status line and widget while the subprocess is running
+
+## Install
+
+### Standalone npm package
+
+```bash
+pi install npm:@diegopetrucci/pi-contrarian
+```
+
+### Collection package
+
+```bash
+pi install npm:@diegopetrucci/pi-extensions
+```
+
+### GitHub package
+
+```bash
+pi install git:github.com/diegopetrucci/pi-extensions
+```
+
+Then reload pi:
+
+```text
+/reload
+```
+
+## Usage
+
+Ask pi normally, for example:
+
+- `Use the contrarian to stress-test this refactor plan.`
+- `Ask contrarian for the strongest opposing case before we commit to this design.`
+- `Have contrarian review my bug hypothesis and identify what evidence could disprove it.`
+
+The main agent can call the tool directly.
+
+## User defaults
+
+Use `/contrarian` to set persisted defaults that apply to future contrarian tool calls, including calls the agent launches automatically without per-call overrides.
+
+```text
+/contrarian status
+/contrarian model anthropic/claude-opus-4-8
+/contrarian thinking high
+/contrarian thinking auto
+/contrarian clear model
+/contrarian clear thinking
+/contrarian clear
+```
+
+Use `/contrarian-model` inside pi to see what it would pick right now.
+
+Tool-call parameters still win over these defaults. `auto` clears the configured default and restores the built-in selection behavior. Preferences are saved under pi's agent directory in `extensions/contrarian.json`.
+
+## Tool parameters
+
+- `task` - required prompt for the contrarian
+- `includeBash` - optional, adds `bash` for non-mutating inspection
+- `model` - optional explicit model override; falls back to the `/contrarian model` default, then auto-selection
+- `thinkingLevel` - optional reasoning/thinking override; falls back to the `/contrarian thinking` default, then built-in defaults
+- `cwd` - optional working directory override
+
+## Notes
+
+- The contrarian is intentionally **read-only**.
+- It never implements fixes or produces patches.
+- Its output separates confirmed objections, plausible concerns, and unresolved unknowns.
+- It is best for adversarial review before committing to a plan, design, or conclusion.