AI-Rig

🚀 What This Setup Enables

Things not possible with vanilla Claude Code:

• Parallel multi-specialist PR review with convergence callouts. /oss:review fans six specialist agents — architecture, tests, perf, docs, lint, security — plus an independent Codex pre-pass, all running simultaneously. The consolidator flags every finding that two or more reviewers independently raised. You see both per-dimension analysis and the overlap, in one report.

• Feature development that cannot skip the demo test. /develop:feature requires a failing demo test to exist and pass review before a single line of production code is written. The gate is structural — the workflow does not proceed to implementation without it.

• Metric-driven experiment loops that auto-rollback on regression. /research:run proposes a change, applies it, measures the target metric, and automatically reverts if the metric regresses — then tries the next hypothesis. The loop runs unattended; you set the goal and the guard, and review the committed result.

• Agent calibration benchmarks that measure overconfidence and fix it. /foundry:calibrate generates synthetic problems, scores each agent's responses against ground truth, and computes the gap between stated confidence and actual recall. Agents that are systematically overconfident get concrete fix proposals — applied automatically with --apply.

Install Claude Code

npm install -g @anthropic-ai/claude-code

2. Install plugins — pick what you need

claude plugin install foundry@borda-ai-rig # base agents + audit, manage, calibrate, brainstorm, … claude plugin install oss@borda-ai-rig # OSS workflow: analyse, review, resolve, release claude plugin install develop@borda-ai-rig # development: feature, fix, refactor, plan, debug claude plugin install research@borda-ai-rig # ML research: topic, plan, judge, run, sweep claude plugin install codemap@borda-ai-rig # structural index: import graph, blast-radius scores

> [!NOTE]
>
> **Safe to install alongside any existing Claude Code setup.** Plugins live in a private cache (`~/.claude/plugins/cache/<plugin>/`) under their own namespace. Your existing `~/.claude/agents/`, `~/.claude/skills/`, and `settings.json` are never modified or overwritten — custom agents and skills you have created remain fully independent. See the [Claude Code plugin reference](https://code.claude.com/docs/en/plugins-reference) for details.

**3. One-time settings merge** — run inside Claude Code:

OSS, develop, and research skills always use their plugin prefix (`/oss:review`, `/develop:fix`, `/research:run`). Safe to re-run.

> [!IMPORTANT]
>
> **Codex CLI** — optional companion; requires a local clone (`.codex/` config is not a plugin):
>
> 

→ See Token Savings (RTK) for RTK install details.

Install

npm install -g @openai/codex          # install Codex CLI
cp -r Borda-AI-Rig/.codex/ ~/.codex/ # activate globally from the project source of truth

This repo's .codex/ directory is the source of truth; ~/.codex/ is a downstream copy. After pulling updates, re-apply: cp -r Borda-AI-Rig/.codex/ ~/.codex/ — or rsync -av to preserve local customizations.

Session-only (no install, for development)

git clone https://github.com/Borda/AI-Rig Borda-AI-Rig
claude --plugin-dir ./Borda-AI-Rig/plugins/foundry

Uninstall

claude plugin uninstall foundry
claude plugin uninstall oss
claude plugin uninstall develop
claude plugin uninstall research
claude plugin uninstall codemap

Settings added by /foundry:setup remain in ~/.claude/settings.json; remove manually if desired. If /foundry:setup was run, symlinks in ~/.claude/agents/ and ~/.claude/skills/ also persist and will be broken after uninstall — remove with rm ~/.claude/agents/<name>.md and rm -rf ~/.claude/skills/<name> for each.

______________________________________________________________________

⚡ Quick Start

```bash

Usage

Mirrored skills are prompt-based — not slash commands:

codex                                                        # interactive — auto-selects agents
codex "use the qa-specialist to review src/api/auth.py"      # address agent by name
codex --profile deep-review "full security audit of src/api/" # activate a profile

run investigate on this branch and find root cause of failing CI
run investigate before fixing this failing pytest; do not suggest a workaround unless it is explicitly temporary
run resolve for the current working tree and fix high-severity findings

→ Deep reference — agents, profiles, adversarial review, mirrored skills, RTK integration: .codex/README.md

Codex CLI plugin

openai/codex-plugin-cc connects the Codex CLI to Claude Code as a local plugin — enabling the cross-validation, mechanical delegation, and diff pre-pass described in Claude + Codex Integration.

→ Install: /plugin marketplace add openai/codex-plugin-cc → /plugin install codex@openai-codex → /reload-plugins

[!NOTE] RTK only compresses Bash tool output — shell commands like git, cargo, pytest, etc. It does not affect Claude Code's native tools (Read, Grep, Glob, Edit, Write), which run inside Claude's own engine and are already token-efficient by design.

🔁 Daily OSS Workflow

A typical maintainer morning — 15 new issues, 3 PRs waiting, a release due:

```text

Common Workflow Sequences

Skills chain naturally — the output of one becomes the input for the next.

<details> <summary><strong>Bug report → fix → validate</strong></summary>

/oss:analyse 42            # understand the issue, extract root cause hypotheses
/develop:fix 42            # reproduce with test, apply targeted fix
/oss:review                # validate the fix meets quality standards

</details>

<details> <summary><strong>Code review → fix blocking issues</strong></summary>

/oss:review 55                                           # 7 agent dimensions + Codex co-review
/develop:fix "race condition in cache invalidation"      # fix blocking issue from review
/oss:review 55                                           # re-review after fix

</details>

<details> <summary><strong>Fuzzy idea → spec → breakdown → implement</strong></summary>

```text /foundry:brainstorm "add caching layer to the data pipeline"

| 1 | audit existing pipeline | /foundry:audit |

🤝 Claude + Codex Integration

Claude and Codex complement each other — Claude handles long-horizon reasoning, orchestration, and judgment calls; Codex handles focused, mechanical in-repo coding tasks with direct shell access.

Every skill that reviews or validates code uses a three-tier pipeline:

• Tier 0 (mechanical git diff --stat gate)
• Tier 1 (codex:review pre-pass, ~60s, diff-focused)
• Tier 2 (specialized Claude agents).

Cheaper tiers gate the expensive ones — this keeps full agent spawns reserved for diffs that actually need them. → Full architecture with skill-tier matrix: .claude/README.md → Tiered review pipeline

Why unbiased review matters / Real example: Claude makes targeted changes with intentionality — it has a mental model of which files are "in scope". Codex has no such context: it reads the diff and the codebase independently. During one session, Claude applied a docstring-style mandate across 6 files and scored its own confidence at 0.88. The Codex pre-pass then found skills/develop/modes/feature.md still referencing the old style — a direct miss. The union of both passes is more complete than either alone.

Two integration patterns make this pairing practical

1. Offloading mechanical tasks from Claude to Codex

Claude identifies what needs to change and delegates execution to the plugin agent. Claude keeps its context clean and validates the output via git diff HEAD.

Dispatched automatically by /oss:review, /oss:resolve, /calibrate, and /research:run via codex-delegation.md. The plugin agent has full working-tree access.

1. Codex reviewing staged work

After Claude stages changes, codex:review --wait serves as a second pass — examining the diff, applying review comments, or resolving PR conflicts. The /oss:resolve skill automates this: it resolves conflicts semantically (Claude) then applies review comments (plugin agent).

   /oss:resolve 42   # Claude resolves conflicts → plugin agent applies review comments
   /oss:resolve "rename the `fit` method to `train` throughout the module"
   

<details> <summary><strong>Setup requirement</strong></summary>

Install the Codex plugin in Claude Code:

/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins

Without the plugin: pre-pass review is skipped gracefully (skills check with claude plugin list | grep 'codex@openai-codex'); /oss:resolve's review-comment step is skipped (conflict resolution works with Claude alone).

</details>

🔌 Plugin Management

vs. vanilla Claude Code

clarifying questions → 2–3 approaches → spec saved to .plans/blueprint/ → curator review → approval

/foundry:brainstorm breakdown .plans/blueprint/2026-04-01-caching-layer.md