Capability Reference

Everything Plan Forge can do — tools, commands, agents, skills, telemetry, and integrations. One page, complete coverage.

14 MCP Tools 19 Agents 8 Skills 8 Dashboard Tabs Quorum Mode

16s

3 slices executed

24/24

pipeline gates pass

self-tests passing

AI models supported

MCP Tools

All tools callable via Copilot Chat, Claude, Cursor, or any MCP client. Start with forge_capabilities for full discovery.

forge_capabilities

Full API surface — tools, workflows, config, memory, glossary

forge_run_plan

Execute plan — DAG scheduling, gates, token tracking, retry

forge_abort

Abort active execution between slices

forge_plan_status

Latest run status from .forge/runs/

forge_cost_report

Spend by model, monthly aggregation

forge_smith

Environment diagnostics + actionable fixes

forge_validate

Setup file validation

forge_sweep

TODO/FIXME/stub marker scanner

forge_status

Phase status from roadmap

forge_diff

Scope drift detection

forge_analyze

Consistency scoring (0-100)

forge_ext_search

Browse extension catalog

forge_ext_info

Extension details

forge_new_phase

Create plan + roadmap entry

Autonomous Execution

Full Auto

One command. pforge run-plan spawns gh copilot CLI for each slice. Gates validate at every boundary. Supports Claude, GPT, and Gemini via --model.

Assisted

You code in VS Code Copilot. Orchestrator prompts you per slice and validates gates automatically. Best of both: human creativity + automated quality.

Parallel

[P]-tagged slices run concurrently. DAG-aware scheduling with scope conflict detection. Up to maxParallelism: 3 workers.

Quorum Mode

Multi-model consensus: dispatch complex slices to 3 AI models for independent analysis, synthesize the best approach, then execute with higher confidence. A/B tested: +20% more tests, better code structure, fewer brittle patterns vs single-model execution.

// Quorum workflow per slice

executeSlice(slice)

│

├─ scoreComplexity() → 1-10 score (7 weighted signals)

│

├─ score < threshold → normal execution

└─ score ≥ threshold → quorumDispatch()

│

├─ Claude Opus 4.6 → dry-run plan ─┐

├─ GPT-5.3-Codex → dry-run plan ─┼─ Promise.all()

└─ Claude Sonnet → dry-run plan ─┘

│

quorumReview() ← synthesize best approach per file

│

spawnWorker(enhancedPrompt) ← execute with consensus

│

gate ✓

Complexity Scoring

7 weighted signals: file scope (20%), cross-module deps (20%), security keywords (15%), database keywords (15%), gate count (10%), task count (10%), historical failure rate (10%).

Auto Mode

--quorum=auto triggers quorum only on high-complexity slices (score ≥ 7). Simple CRUD runs normally. Best of both: quality where it matters, speed where it doesn't.

Graceful Degradation

If <2 models respond, falls back to normal execution. If reviewer fails, uses best single dry-run. No model unavailability blocks your pipeline.

A/B Tested

Invoice Engine (rate tiers, discounts, tax, rounding): quorum produced 20% more tests, extracted DRY helpers, used idiomatic .NET patterns, and caught edge cases the single model missed.

A/B Test: Invoice Engine (4 slices, rate tiers + discounts + tax + banker's rounding)

Metric	Standard	Quorum (3 models)	Delta
Pass rate	4/4	4/4	Tie
Duration	12 min	32 min	+168%
Tests generated	15	18	+20%
DRY helpers	Inline	Extracted	Better
Test dates	Hardcoded (fragile)	Relative (robust)	Better
Edge case coverage	Standard	+voided regen, +sequence	Better

Live Dashboard

localhost:3100/dashboard — 8 tabs, real-time via WebSocket, no build step required.

📊

Progress

Live slice cards

📋

Runs

History table

💰

Cost

Model breakdown

⚡

Actions

One-click tools

🔄

Replay

Session logs

🧩

Extensions

Catalog browser

⚙️

Config

Visual editor

🔍

Traces

OTLP waterfall

Agents & Skills

19 Reviewer Agents

Stack (6): architecture, database, deploy, performance, security, test-runner

Cross-stack (8): accessibility, API contracts, CI/CD, compliance, dependency, error handling, multi-tenancy, observability

Pipeline (5): specifier → plan-hardener → executor → reviewer-gate → shipper

8 Slash Command Skills

/database-migration · /staging-deploy · /test-sweep

/dependency-audit · /code-review · /release-notes

/api-doc-gen · /onboarding

Observability & Memory

OTLP Telemetry

Every run produces trace.json with resource context, span kinds (SERVER/INTERNAL/CLIENT), severity levels, and log summaries.

Per-run manifest + global index (append-only, corruption-tolerant)
Dashboard Traces tab with waterfall timeline
Optional OTLP collector forwarding (Jaeger, Aspire, Grafana)

OpenBrain Memory

Optional persistent semantic memory. Decisions and patterns captured in one session are searchable in every future session.

Auto-search before each slice for prior conventions
Auto-capture decisions after each slice
Cost anomaly detection (>2x average triggers insight)
Run summary captured for future phase planning

Stack Presets

Preset	Instructions	Agents	Prompts	Skills
.NET	17	19	15	8
TypeScript	18	19	15	8
Python	17	19	15	8
Java	17	19	15	8
Go	17	19	15	8
Azure IaC	12	18	6	3

Ready to forge?

Get Started GitHub

Machine-readable: forge_capabilities MCP tool · .well-known/plan-forge.json