Open-source AI operations platform built on Claude Code. 107 skills, 27 agents, security built in. Linux / macOS / WSL.
This repository also configures its own agents. See what Forge tells them →
Skill Claude Code
Adversarial analysis with parallel agents to stress-test ideas and strategies. USE WHEN user mentions red team, devil's advocate, adversarial analysis, stress test idea, challenge proposal, poke holes, find weaknesses, OR wants critical evaluation of plans, proposals, strategies, or arguments.
Skill Claude Code
Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available researcher agents. Deep content analysis with extended thinking. Intelligent retrieval for difficult sites. Fabric pattern selection for 242+ specialized prompts. USE WHEN user says 'do research', 'extract…
Skill Claude Code
Generate performance review documents from evidence sources. USE WHEN user mentions review brief, performance review, self-review, team assessment, OR brag doc compilation. Produces manager-ready or peer-style review documents.
Skill Claude Code
Expert SOC 2 compliance assistant covering all five Trust Services Criteria (Security/CC, Availability/A, Confidentiality/C, Processing Integrity/PI, Privacy/P). Use this skill whenever a user mentions SOC 2, Trust Services Criteria, SOC 2 Type 1 or Type 2, audit readiness, compliance gaps, control documentation…
Skill Claude Code
Expert SWIFT Customer Security Programme (CSP) advisor covering the Customer Security Controls Framework (CSCF v2025). Use this skill whenever a user asks about SWIFT CSP, CSCF controls, SWIFT security attestation, KYC-SA portal, SWIFT architecture types (A1/A2/A3/A4/B), mandatory vs advisory controls, independent…
Skill Claude Code
Semantic search, temporal knowledge graph, layered context loading, and cross-project tunnels across PAI history, learnings, research, and Obsidian notes. USE WHEN user asks about past work, previous sessions, what they've done before, OR user wants to recall, remember, find, or search history OR user mentions…
Skill Claude Code
Search PAI session history using jq queries and text search. USE WHEN user mentions search history, find sessions, session logs, past conversations, cost tracking, tool usage statistics, what did I work on, OR wants to analyze previous PAI sessions.
Skill Claude Code
Create compelling story-format summaries using UltraThink to find the best narrative framing. Support multiple formats - 3-part narrative, n-length with inline links, abridged 5-line, or comprehensive via Foundry MCP. USE WHEN user says 'create story explanation', 'narrative summary', 'explain as a story', or wants…
Skill Claude Code
Execute implementation plans by dispatching fresh subagent per task with two-stage review (spec compliance + code quality). USE WHEN user has a plan with independent tasks that can be executed in the same session, OR wants to implement features using TDD with isolated context per task. Fresh context per task prevents…
Skill Claude Code
Expert TSA cybersecurity compliance advisor for critical infrastructure owners and operators. Use this skill whenever a user asks about TSA Security Directives for pipelines, freight railroads, passenger rail, public transit, or bus operators; the TSA Cyber Risk Management Program (CRMP); Cybersecurity Implementation…
Skill Claude Code
Bidirectional Telegram bot for full PAI access. USE WHEN user mentions telegram bot, start telegram, stop telegram, telegram access, remote PAI, mobile PAI, OR wants to manage the telegram bot service (start/stop/restart), OR needs to save telegram results to obsidian.
Skill Claude Code
Send PAI system status updates to Telegram with on-demand or scheduled delivery. USE WHEN user says 'send status to telegram', 'telegram update', 'schedule daily telegram', 'setup telegram cron', or requests PAI status notifications via Telegram. Includes system health checks, formatted messages with timestamps, and…
Skill Claude Code needs its repo
Enforces evidence-based completion claims with mandatory verification gates. USE WHEN completing any task, claiming results, reporting success, OR before declaring work done. Prevents rationalization and false completion. Iron Law: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. Run the command, read the…
Skill Claude Code
Real-time Wazuh SIEM security dashboard with PAI chat integration. USE WHEN user mentions wazuh dashboard, security alerts, SIEM monitoring, alert analysis, OR wants to view security events with AI assistance.
Skill Claude Code
Development workflow methodology enforcing plan-first execution, subagent strategy, self-improvement loops, verification gates, and elegant solutions. USE WHEN developing applications, writing code, implementing features, fixing bugs, building systems, OR when user mentions workflow, development process, coding…
Skill Claude Code
Structures detailed implementation plans for multi-step development work. USE WHEN user needs implementation plan, development roadmap, feature breakdown, OR wants to plan before implementing. Creates granular task lists (2-5 min each) with exact file paths, complete code, expected output. TDD, DRY, YAGNI methodology.…
Skill Claude CodeCodex
Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
Skill Claude Code
Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly…
Skill Claude Code
Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time".
Skill Claude Code
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. 100ms per command. Use when you need to test a…
Skill Claude Code
Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify…
Skill Claude Code
Visual layer of the wiki. Add images, text cards, PDFs, and wiki pages to Obsidian canvas files with auto-positioning inside zones. Integrates with /banana for image capture. Triggers on: /canvas, canvas new, canvas add image, canvas add text, canvas add pdf, canvas add note, canvas zone, canvas list, canvas from…
Skill Claude Code
Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety…
Skill Claude Code
Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: