Skip to main content
plugin

bullpen — Claude Code plugin: what it does, how to install

bullpen — a set of skills that brings senior engineer instincts into Claude Code. It helps challenge bad assumptions, attack code before shipping, and verify results before marking tasks done.

MIT ★ 1,013 updated 2026-08-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add ccplugins/awesome-claude-code-plugins
/plugin install bullpen@awesome-claude-code-plugins
Open on GitHub

What bullpen does

The plugin introduces skills that mirror senior engineering habits into Claude Code. /skeptic pushes back on incorrect premises in a prompt, /closer refuses to mark work complete without running the code and inspecting output, and /attacker probes fresh logic for edge cases or vulnerabilities. When repeated edits fail, /stop-digging halts the loop and triggers a clean re-diagnosis.

Every skill supports three intensity modes: lite, full, and ultra. The full mode applies by default. The repository contains no hooks or MCP servers, relying entirely on individual SKILL.md files. Skills run automatically when a task matches their description, or developers can invoke them directly in the prompt.

What it helps with

  • challenge flawed task assumptions before writing code
  • expose vulnerabilities and edge cases in newly generated logic
  • require working runtime output before claiming a task is done
  • stop repetitive failing repair attempts and re-diagnose the bug
  • verify third-party API methods before calling them

Example prompts for the agent

  • /skeptic ultra verify the design of the new auth service
  • /attacker check the endpoint for vulnerabilities before committing
  • /closer lite

How to install bullpen

Plugin marketplace

/plugin marketplace add ccplugins/awesome-claude-code-plugins
/plugin install bullpen@awesome-claude-code-plugins

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about bullpen

How do I install bullpen in Claude Code?

Register the marketplace via /plugin marketplace add ccplugins/awesome-claude-code-plugins and install the plugin with /plugin install bullpen@awesome-claude-code-plugins.

What does bullpen do?

It equips Claude Code with skills that challenge wrong assumptions, probe code for weaknesses, verify execution results, and prevent endless failed repair loops.

How do you deactivate a skill during a session?

Enter stop attacker or replace the skill name with the one currently active to return the agent to its standard behavior.

Source text

bullpen · MIT
<h1 align="center">Bullpen</h1>

<p align="center"><em>The senior dev, unbundled.</em></p>

<p align="center">
  One lazy senior dev makes your agent write less code.<br>
  A whole bullpen makes it think like the room.
</p>

---

Ponytail put the laziest senior dev inside your agent — the one who replaces fifty
lines with one. But that engineer is only one seat in the room. The same senior
also **pushes back on bad ideas, refuses to fake "done," attacks their own code,
asks before guessing, and stops digging when the hole gets deep.**

Bullpen is that room. Ten small, opinionated skills — each one instinct of a
senior engineer — that you call in by name, at the intensity you want.

## The roster

| Skill | The instinct | Thesis |
|-------|-------------|--------|
| **`/skeptic`** | Pushes back on the request when it encodes a wrong assumption | Your AI shouldn't be a yes-man. |
| **`/closer`** | Won't claim "done" until it ran the code and showed the output | "It works" is not a claim. It's a screenshot. |
| **`/attacker`** | Attacks its own code before shipping; fixes what lands | Ship code that already survived an attack. |
| **`/fact-checker`** | Verifies an API exists before calling it | It reads the docs so you don't debug the fiction. |
| **`/interrogator`** | Asks the few decisive questions before building | The most expensive code solved the wrong problem. |
| **`/stop-digging`** | Stops re-trying after two failed fixes and re-diagnoses | When you're in a hole, stop digging. |
| **`/doorman`** | Justifies every new dependency against what's already there | Every dependency is a liability you'll maintain forever. |
| **`/historian`** | Finds out why odd code exists before deleting it | Don't remove the fence until you know why it's there. |
| **`/chameleon`** | Writes code indistinguishable from the codebase around it | The best contribution is invisible. |
| **`/explainer`** | Splits work into reviewable commits a human can follow | Write for the reviewer, not the compiler. |

Each skill takes an intensity argument — **lite** (name the better move, you
decide), **full** (the discipline enforced; the default), **ultra** (the
extremist version, with the proof). Pair them freely: `/attacker` hardens what
`/ponytail` keeps lazy; `/skeptic` decides *whether* to build, `/interrogator`
clarifies *what*, `/closer` proves it's *done*.

## See it

One before/after per skill in [`examples/`](examples/) — the naive output, then
the same task with the skill on. Start with
[the Attacker](examples/attacker.md) (an IDOR + an injection, fixed at the
boundary) or [the Skeptic](examples/skeptic.md) (a cache request answered with
the index that was the real fix).

## Install

**As a Claude Code plugin:**

```
/plugin marketplace add faizanmohiuddin482/bullpen
/plugin install bullpen@bullpen
```

Or from a local clone:

```
/plugin marketplace add ./bullpen
/plugin install bullpen@bullpen
```

Then the skills are available. They fire automatically when a task matches (the
`description` in each `SKILL.md` is the trigger), or call one by name:

```
/attacker              # full intensity on this task
/skeptic ultra         # make it defend the premise
/closer lite           # just tell me verified vs assumed
stop attacker          # revert to normal mode
```

## How it's built

Bullpen ships **one canonical `SKILL.md` per skill** — nothing else. No hooks, no
MCP server, no per-platform copies, no version files to hand-sync. The design rule
is simple: never duplicate a skill's text, so it can never drift.

The only build check is [`scripts/check-skills.js`](scripts/check-skills.js): it
confirms each skill has the required frontmatter and house sections.

- Add a skill → one folder, one `SKILL.md`, following [`AUTHORING.md`](AUTHORING.md).
- Change a skill → edit one file.
- That's the whole contract.

## License

MIT.

<p align="center"><sub>The only code you trust is the code you already tried to break.</sub></p>

© Mohammed Faizan Mohiuddin · MIT · ccplugins/awesome-claude-code-plugins

Similar plugins

All plugins for Agent setup: memory, context, orchestration →

From the same set184

The whole set →
community-building-strategist community-building-strategist — a slash command that interviews you about community goals, then turns the answers into an HTML strategy: platform, channels, roles, rituals, moderation, metrics. CX Codex +1 ★ 1,013repo stars session-tax session-tax measures token overhead in Claude Code opening context before you type. It reveals how many tokens load from unused skills, hooks, and tool schemas. ★ 1,013repo stars claude-session-tint claude-session-tint is a Claude Code plugin that colors Terminal.app windows by project and highlights a window when a reply arrives out of focus. Shared-window tabs get a title marker instead. ★ 1,013repo stars rote rote turns a skill you already trust into a deterministic pipeline with no model in the loop, then serves the compiled result back to Claude as an MCP tool. ★ 1,013repo stars slicewise slicewise breaks feature work into small slices, runs a test gate, compares two independent reviews, and leaves the commit decision to you. ★ 1,013repo stars craftsman craftsman is a Claude Code plugin with agents, skills and hooks that keeps changes within scope, finds a bug's root cause and reports what was verified. ★ 1,013repo stars fable-baton fable-baton turns Fable 5 into an orchestrator in Claude Code, routing implementation to tiered Opus, Sonnet, and Haiku subagents. ★ 1,013repo stars claude-bionify claude-bionify is a Claude Code plugin that applies bionic reading to model responses. It bolds the start of each word in the live terminal stream to guide eye fixations. ★ 1,013repo stars

Project sponsors

Companies that keep this analytics open