Skill Claude CodeCodex
Runs the autonomous aspiration loop — the perpetual heartbeat that selects, executes, verifies, reflects on, and evolves goals forever. This is the core orchestrator for autonomous mode. Use whenever /boot finishes in autonomous mode, when re-entering the loop after autocompact recovery, or when the user runs…
Skill Claude CodeCodex
Generates a complete sprint-planning backlog as copy-pasteable markdown: all aspirations, goals, scores, blockers, and user action items, written to {agent}/BACKLOG.md with a compact terminal summary. Use whenever the user says "show me the backlog", "give me sprint planning material", "what's in the queue", or needs…
Skill Claude CodeCodex
Entry point for autonomous mode — runs the status report (hypothesis readiness, pipeline state, accuracy stats, meta-memory counts), invokes /prime for full context load, then hands off to the /aspirations loop. Use only when /start activates autonomous mode or when recovering the loop after autocompact. NEVER invoke…
Skill Claude CodeCodex
Creates new aspirations from three source modes — from-user (parse user text), from-self (autonomous gap-driven, optionally --plan for research-backed deliberation), and from-followup (fast-path: one aspiration with a single 'Design implementation plan and file sub-goals here' seed goal). USE WHENEVER you catch…
Skill Claude CodeCodex
Evaluates all graduation gates for the agent's current curriculum stage and promotes to the next stage if every gate passes. Gates include metricthreshold, countcheck, logscan, and commandcheck types. Use whenever /aspirations-consolidate hits session end, /aspirations-evolve runs a mandatory evolution pass, or the…
Skill Claude CodeCodex
Performs HTN (Hierarchical Task Network) decomposition: breaks a compound goal into a sequence of primitive, directly-executable sub-goals. Use whenever a selected goal is too abstract or multi-step to execute as-is (selector or Phase 4 flags it as compound), the user says "break down this goal", or…
Skill Claude CodeCodex
Drains the agent's temp/ working-doc store into the knowledge tree. Walks every undrained file under agents/{agent}/temp/ (analyses, briefings, audits, design docs, snapshots), classifies each against the learning-routing decision tree, encodes its reusable value into the right store (knowledge tree / reasoning bank /…
Skill Claude CodeCodex
Runs a structured learning pass on the current chat session: encode reusable insights to the knowledge tree / reasoning bank / guardrails / patterns / experience archive; file Maintain goals for inline completions; re-probe blockers our work may have falsified; surface new aspirations / goals / forge gaps; propose…
Skill Claude CodeCodex
Fires whenever the aspirations-precheck cadence hits 75 completed goals — an autonomous structured 7-lane self-audit that converts the user's proven-high-yield diagnostic question into a routine. Sweeps memory hygiene (including insight curation from agents/{agent}/insights.jsonl — distills unprocessed entries into…
Skill Claude CodeCodex
Forges a new SKILL.md from a recurring capability gap recorded in meta/skill-gaps.yaml, registers it in world/forged-skills.yaml, creates companion scripts for restricted operations, announces on the message board, and adds a validation goal. Use whenever a gap reaches the forge threshold (timesencountered >= 2…
Skill Claude CodeCodex
Use whenever a specific artifact set needs adversarial bug-hunt review — on-demand fresh-eyes code review that mode-flips the reviewing agent into adversarial posture (not confirmation) and systematically probes error paths, edge cases, platform-specific behavior (Windows subprocess / CRLF), locking, race conditions…
Skill Claude CodeCodex
Periodic local self-audit of world/program.md — fires when the every-100-goals precheck cadence trips, or on user demand (/fresh-eyes-program). Assembles a briefing (The Program body, both agents' Self summaries, cross-agent aspiration portfolio, recent completions, drift signals), writes it to agents/{agent}/temp/ (a…
Skill Claude CodeCodex
Periodic local self-audit (cadence: every 25 goals). Assembles a portfolio-direction briefing (Self snapshot, aspiration portfolio, evolution signals, partner activity), writes it to agents/{agent}/temp/ (a staging file drained to the knowledge tree), and posts a one-line summary to the coordination board. No email…
Skill Claude CodeCodex
Periodic local self-audit of the knowledge tree's top-level taxonomy — fires when the every-200-goals precheck cadence trips, or on user demand (/fresh-eyes-tree). Assembles a briefing covering L1 distribution skew (S1), L1 pick-rate trends (S9), candidate L2 promotions, candidate L1 retirements, and SPROUT/REPARENT…
Skill Claude CodeCodex
Supply-side domain goal generation: read the domain's product surfaces through six generation lenses (metric-driven, journey-driven, code-reality, revenue-path, distribution, critic), generate evidence-backed user-story candidates, adversarially VERIFY every evidence claim BEFORE filing, then file survivors into the…
Skill Claude CodeCodex
Shows the user dashboard: pending questions the agent has logged for the user, goals with participants including user, and blocked goals grouped by blocker reason. Use whenever the user says "what do you need from me", "what's blocked", "what questions do you have", "what am I on the hook for", or invokes…
Skill Claude CodeCodex
Primes the agent's active context by loading accumulated knowledge: self.md identity, world/program.md shared purpose, a bounded 100%-coverage guardrail index (expanded in full on demand), a bounded recency slice of the reasoning bank, category-specific tree nodes (top in-progress and HIGH-priority pending goal…
Skill Claude CodeCodex
Shows the priority dashboard (all active aspirations ranked by aggregate goal score) and lets the user interactively reorder priorities to update the aspiration queue. Use whenever the user says "what are you working on next", "re-rank my priorities", "show me the priority dashboard", "show the queue", or invokes…
Skill Claude CodeCodex
Performs maintenance reflection: curates memory (reasoning-bank entries, tree nodes, pattern signatures), applies active forgetting to low-utility items, grooms aspirations, and detects stuck goals that may need unblock conversion or archival. Use whenever the loop hits the maintenance cadence, the reasoning bank…
Skill Claude CodeCodex
Reflects on a just-resolved hypothesis or goal outcome: builds the Antecedent-Behavior-Consequence (ABC) chain, captures execution pattern signatures, and processes batched micro-hypotheses. Use whenever a hypothesis resolves in the pipeline and reflection depth is "outcome" (not full self-model reflection), or…
Skill Claude CodeCodex
Runs deep self-model reflection: synthesizes patterns across recent outcomes, extracts strategies into the archive, updates the Level 2 self-model, and calibrates confidence scores. Use whenever the loop hits the self-reflection cadence, sq-012 fires ("does this outcome change my core purpose?"), cumulative learning…
Skill Claude CodeCodex
Implements the Shared Tree Update Protocol used by every reflection path: identifies the affected knowledge-tree node, updates the target's content and metadata, propagates signals upward through parent nodes, and logs capability events. Use whenever any reflection or encoding writes to a tree node and parents must…
Skill Claude CodeCodex
Orchestrates Reflexion-based learning: dispatches to /reflect-on-outcome (hypothesis ABC chains, execution patterns, batch micro-hypotheses), /reflect-on-self (pattern synthesis, Level 2 self-model, calibration), or /reflect-maintain (memory curation, active forgetting, aspiration grooming) based on --mode. Use…
Skill Claude CodeCodex
Performs hippocampal replay on resolved hypotheses: compressed sharp-wave review for reconsolidation, reverse-order recency scan, selective encoding-queue replay, category-scoped replay, or domain-transfer bundling. Use whenever the aspirations loop hits the replay cadence, /aspirations-consolidate schedules a replay…