Agent
Read-only reviewer for audit classifier changes — enforces before/after finding counts and prohibits same-commit masking of product fixes.
5 21d ago A 30 tokens
original MIT
Agent
Read-only plan health auditor — analyzes run history, failure modes, gate-portability issues, and slice retry rates, then proposes concrete patches.
5 21d ago A 32 tokens
original MIT
Instructions file GitHub Copilot
Instructions for srnichols/plan-forge, covering instructions for copilot, architecture principles, core principles (non-negotiable), cost estimates and talking to forge-master.
5 21d ago A 2,670 tokens
original MIT
Instructions file GitHub Copilot
Agent-Computer Interface (ACI) rules — how every forge MCP tool must shape its inputs and outputs so the calling agent can use it reliably. Auto-loads when editing tool definitions or capabilities.
5 21d ago A 2,072 tokens
original MIT
Instructions file GitHub Copilot
AI Plan Hardening Runbook quick reference — auto-loads when editing plan files.
5 21d ago A 503 tokens
original MIT
Instructions file GitHub Copilot
Core architecture principles — Architecture-First Approach, Separation of Concerns, TDD, Best Practices over Quick Wins. READ BEFORE any code changes.
5 21d ago A 3,872 tokens
original MIT
Instructions file GitHub Copilot
Clean Code guardrails — function design, naming, commenting, and review checklist derived from the Phase 42 audit (Clean Code, Robert C. Martin).
5 21d ago A 1,500 tokens
original MIT
Instructions file GitHub Copilot
Context management for AI agents — recognize context degradation, prioritize instructions, bridge sessions with memory.
5 21d ago A 767 tokens
original MIT
Instructions file GitHub Copilot
Git workflow and commit conventions — conventional commits, push reminders, version-aware messaging.
5 21d ago A 497 tokens
original MIT
Instructions file GitHub Copilot
Project Principles — auto-loads governing principles when docs/plans/PROJECT-PRINCIPLES.md exists.
5 21d ago A 257 tokens
original MIT
Instructions file GitHub Copilot
Plan Forge release procedure — auto-loads when editing release-related files. Maintainer-only; NOT shipped to consuming projects.
5 21d ago A 2,058 tokens
original MIT
Instructions file GitHub Copilot
Security rules for Plan Forge — input validation, command-injection avoidance, secret handling, and the "mutate user repo" contract. Auto-loads broadly because every file is a potential boundary.
5 21d ago B 2,080 tokens
original MIT
Instructions file GitHub Copilot
Self-repair reporting — when and how to file meta-bugs against Plan Forge itself using forgemetabugfile.
5 21d ago A 1,327 tokens
original MIT
Instructions file GitHub Copilot
Standard output templates for orchestration status updates, progress reports, blockers, completions, handoffs, and failure reports. Use these formats during plan execution, multi-agent runs, and autonomous operations.
5 21d ago A 1,373 tokens
original MIT
Instructions file GitHub Copilot
Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.
5 21d ago A 3,216 tokens
original MIT
bug-fix
16Skill Claude CodeCodex
Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.
5 21d ago A 80 tokens
original MIT
Skill Claude CodeCodex
Run a comprehensive Clean Code audit against the codebase — module size, function complexity, long parameter lists, TODO/FIXME markers, commented-out code, duplication (DRY), Boy Scout delta, dead exports, test smells, shell-parity (PS/Bash twins), dep boundaries (cross-package imports), frozen-arrays drift…
5 21d ago A 92 tokens
original MIT
code-review
18Skill Claude CodeCodex
Plan-Forge-tuned comprehensive code review — runs public-surface diff, forge analysis, architecture / security / testing / patterns checks, plus Plan-Forge-specific gates (ACI compliance, dual-shell parity, branch model). Use before merging features or at the end of a phase. With --quorum, dispatches multi-model…
5 21d ago A 70 tokens
original MIT
Skill Claude CodeCodex
Generate a per-organisation stakeholder briefing for Plan Forge from the canonical template, optionally drafting the prospect-specific sections from a source directory of customer materials. Use when an internal champion needs to walk a colleague or VP through the decision to adopt Plan Forge.
5 21d ago A 55 tokens
original MIT
Agent
Audit the infra/ folder in an app repo for Azure IaC violations: naming, security, managed identity, secrets exposure.
5 21d ago A 28 tokens
original MIT
Agent
Audit whether key decisions and lessons were captured to persistent memory (OpenBrain) during the phase.
5 21d ago A 22 tokens
original MIT
Agent
Audit code for multi-tenant isolation: query safety, cache scoping, event context, cross-tenant data leakage prevention.
5 21d ago A 29 tokens
original MIT
Agent
Enterprise-grade Azure environment sweeper — WAF + CAF + Landing Zone + Org Rules + Policy + Resource Graph + Telemetry + Remediation. Run on any scope to produce a prioritised findings report with remediation code.
5 21d ago A 48 tokens
original MIT
Agent
Review Bicep templates for best practices: naming, parameters, security, module structure, linter violations, API versions.
5 21d ago A 30 tokens
original MIT