Citadel Harness

Plugin citadel from marketplace citadel-local in SethGammon/Citadel. Commands read from the repo's manifest — 8 days ago.

Skills (48)

• architect

  Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Multi-candidate evaluation for key decisions. - architect - architecture - design the system - file structure - plan the bui

• archon

  Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition. - campaign -

• ascii-diagram

  Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification. - ascii diagram - ascii art - box diagram - architecture diagram - flow di

• autopilot

  Intake-to-delivery pipeline. Processes pending items from .planning/intake/: briefs new ideas, executes approved work through research → plan → build → verify. Drop a file in .planning/intake/ and invoke this skill. - intake - process pending - pipeline

• cost

  Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native session data for exact numbers. Complements /dashboard with focused cost views. - cost - costs - cost breakdown - campaign cost - token usage - b

• create-app

  End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase. Routes through PRD, architecture, and Archon campaign with verification at every step. - create app - build app - build me - make an app - new a

• create-skill

  Creates new skills from the user's repeating patterns. Interview-driven: discovers the task, analyzes failure modes, generates a production SKILL.md, installs it, tests it on a real target, and teaches the user how to use it. Use when a user wants to encode a repeating workflow; do NOT use for one-o

• daemon

  Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion

• dashboard

  Real-time harness observability dashboard. Reads campaigns, fleet sessions, telemetry, and pending queues to present a snapshot of harness state at a glance. Invoked by /dashboard, /do status, or phrases like "what's happening" and "show activity". - dashboard - what's happening - what's going on -

• decision-map

  Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .pla

• deploy-steward

  Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures. - deploy steward - deploy queue - merge steward - mainline steward

• design

  Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations. - design - style guide -

• do

  Unified router that auto-routes user intent to the right direct action, skill, orchestrator, or explicit Operation Control plan. Classifies input by scope, complexity, persistence needs, and parallelism, then dispatches to the cheapest path that can handle it: direct command, skill, marshal, archon,

• doc-gen

  Documentation generator with three modes: function-level (JSDoc/docstrings), module-level (directory READMEs), and API reference (endpoints/exports). Reads existing project doc style and matches it. Never generates docs that just restate what the signature already says. - document - docs - docstring

• evolve

  Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent beli

• experiment

  Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures against a fixed baseline, and retains verified candidates locally. Supports convergence detection and diminishing returns. - experiment - optimize - try - A/B - measure

• fleet

  Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously. - parallel - s

• grill

  Relentless one-question-at-a-time interview that sharpens a vague plan or design into shared understanding before any build. The elicitation engine other planning skills call instead of inventing their own interview. Auto-trigger when the user says "grill me", asks to stress-test a plan, or starts a

• houseclean

  Cross-drive storage audit and cleanup. Surveys all drives, finds orphaned git worktrees, large AI tool caches (.ollama, .gemini, .cursor, npm, pip), and buildable artifacts (node_modules, .venv). Produces a prioritized action plan with specific migration commands. Use when disk space is low or workt

• improve

  Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch. - improve - improvement loop - quality loop - rubric - score against - run impr

• infra-audit

  Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest. - infra - infrastructure - what databases - what systems - docker-compos

• learn

  Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmo

• live-preview

  Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool. - preview - screenshot - visual check - does it render

• loop

  Bounded foreground repetition for the current session. Creates a loop contract, runs or coordinates an action plus verifier up to a declared attempt limit, and records evidence under .planning/loops/. Use for repeat-until-pass work that is too small for daemon and not time-based scheduling. - loop -

• map

  Structural codebase index generator. Builds a compact JSON map of files, exports, imports, dependency graph, and roles. Queryable by keyword. Injected into fleet agents as context slices to reduce token usage on code navigation. - map - index codebase - codebase map - structural index - scan codebas

• marshal

  Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator. - orchestrate - chain skills -

• merge-review

  Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes. - merge review - check merges - any conflicts - fleet conflicts - pending

• organize

  Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces;

• postmortem

  Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident. - postmortem - retro

• pr-watch

  Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature. - watch pr - watch ci - monitor pr - fix ci - ci failing - pr failing -

• prd

  Generates a Product Requirements Document from a natural language app description. Asks clarifying questions, researches similar apps, defines scope, stack, architecture, and produces a structured PRD that Archon can decompose into a campaign. - prd - requirements - spec - plan an app - design an ap

• qa

  Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed). - qa - test the app - click t

• refactor

  Safe multi-file refactoring with automatic rollback. Establishes a type/test baseline, plans all changes, executes file-by-file, and verifies zero regressions. Reverts if verification fails after two fix attempts. Handles renames, extracts, moves, splits, merges, and inlines. - refactor - rename - e

• research

  Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. D

• review

  5-pass structured code review — correctness, security, performance, readability, consistency

• scaffold

  Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points. - scaffold - generate component - generate module - generate service - ne

• schedule

  Manages recurring and one-off scheduled tasks. Session-scoped scheduling via CronCreate/CronDelete/CronList. Documents the cloud path for tasks that need to survive machine sleep or network drops. - schedule - recurring - every N minutes - cron - set a reminder - run periodically

• session-handoff

  Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items. - handoff - session summary

• setup

  First-run experience for the harness. Three modes: Recommended (guided, ~3 min), Full Tour (guided + skill walkthrough, ~8 min), and Express (zero questions, ~30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card. - setup -

• systematic-debugging

  4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades. - debug - root cause - diagnose - why is - investigate bug

• telemetry

  Unified telemetry hub. Shows current session cost, today's spend, all-time totals, hook activity, trust level, and a directory of every telemetry command available. Also the control surface to toggle telemetry on/off and tune thresholds. Single entry point for anyone asking "what does this cost" or

• test-gen

  Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns

• triage

  GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code re

• unharness

  Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed

• verify

  Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown. - verify - verify hooks - hook hea

• watch

  File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes;

• wiki

  Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to ~400K words. - wiki - knowledge base - llm wiki - project

• workspace

  Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context. - workspace - multi-repo - cross-repo - across repos - multiple repos - coordi

Subagents (7)

• arbiter

  Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and

• arch-reviewer

  Read-only architecture reviewer. Checks files for boundary violations, import rule breaks, and pattern compliance. Does not modify files. - Edit - Write - Bash - NotebookEdit - Read - Grep - Glob

• archon

  Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do. - Read - Write - Edit - Bash - Glob - G

• fleet

  Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave, collects discoveries, shares context between waves, rebalances priorities. Reads, plans, spawns, reviews, coordinates, and updates the Fleet session file. Source code cha

• knowledge-extractor

  Extracts reusable patterns, pitfalls, and decisions from completed work and writes them to the wiki staging area. Run after finishing a body of work to capture what was learned. Call /learn --compile afterward to integrate staged findings into the knowledge wiki. - Bash - WebSearch - WebFetch - Agen

• phase-validator

  Lightweight handoff validator. Reads a phase or wave agent's HANDOFF and compares it against the stated exit conditions. Returns a structured verdict (pass/fail) with specific reasons. Never modifies files — read-only judge. Spawned by Archon after each phase and by Fleet after each wave agent. - Ba

• policy-enforcer

  Blocking policy judge. Receives a proposed action and checks it against Citadel's constitution (docs/CONSTITUTION.md). Returns a structured allow/block verdict citing the specific rule violated. Never modifies files — read-only judge. Spawned by Archon and Fleet before Red-reversibility operations.

Similar plugins