Claude Code harness that refreshes its own context instead of compacting: at a threshold it writes a verified capsule, runs /clear, and resumes in a fresh session. Memory is plain markdown in git, readable with git log. MIT, runs locally, one install (Node 18+). Codex adapter included.
This repository also configures its own agents. See what aigent-os tells them →
Agent Claude Code
Prompt engineer. Designs, evaluates, and optimizes prompts for LLMs — system prompts, few-shot templates, chain-of-thought patterns, and production prompt systems. Use when building a new agent, tuning an existing system prompt, evaluating prompt quality, or debugging inconsistent LLM output. Reports honesty ledger on…
Agent Claude Code
Scout/reader instrument. Traverses, summarizes, returns structured findings. Never builds. Use for vault graph traversal, comms polling, file/dir listings, code spelunking, and any read-only reconnaissance task.
Agent Claude Code
Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.
Agent Claude Code
Critic and devil's advocate instrument. Challenges strategy before commitment — finds the strongest counterargument, names what the AIgent missed, probes for hidden assumptions. Use before any significant decision. Read-only — she critiques, never builds. Voice is skeptical but constructive.
Agent Claude Code
Visual/design specialist. Designs sprite specs, color systems, UI layouts, animation choreography, and AI image-gen prompts. Use for any task where the output is a visual specification, design brief, or prompt for gpt-image-2/Stable Diffusion. Reports honesty ledger on completion.
Agent Claude Code
Writer/builder instrument. Takes a complete spec, returns a diff or built artifact. Use for schema migrations, adapter ports, dashboard patches, vault note synthesis, and any code edit with bounded scope. Reports honesty ledger on completion.
Agent Claude Code
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
Agent Claude Code
Research synthesist instrument. Multi-source deep dives — Tavily, Defuddle, GitHub, vault prior art — synthesized into structured briefings with citations. Use for tool evaluations, competitive analysis, technology assessments, and any question requiring wide-net research + synthesis. Returns hypothesis + evidence +…
Agent Claude Code
Architecture reviewer. Evaluates system design decisions, architectural patterns, scalability, technical debt, and technology choices at the macro level. Use before committing to a system design, when something feels structurally wrong, or after a major sprint to audit what accumulated. Reports honesty ledger on…
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: