convergence-monitoring is agent-read markdown (skill) from lstr-1/skills: Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive a Stop/Continue/Investigate decision at each inter-wave checkpoint. Distinct from /evolve (retrospective) and session-reviewer (wave output review): convergence-monitoring answers "are we making progress?" not "was the last wave correct?". Primary consumer: /autoresearch loops and wave-executor inter-wave checkpoints..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
> **Platform Note:** State files use the platform's native directory: `.claude/` (Claude Code),
> `.codex/` (Codex CLI), or `.cursor/` (Cursor IDE). Shared metrics live in
> `.orchestrator/metrics/`. See `skills/_shared/platform-tools.md`.
# Convergence-Monitoring Skill
## Platform-native (CC 2.1.105+)
This skill's watcher is registered as a plugin monitor via `.claude-plugin/plugin.json`'s `experimental.monitors` reference to `monitors/monitors.json`. Each session that loads this plugin auto-starts the watcher in the background (see `scripts/lib/convergence-monitor.mjs`). Each NDJSON stdout line from the watcher becomes a `<task_notification>` event Claude sees mid-session.
For harness < 2.1.105 (no monitor support), the skill's manual probes documented below serve as the fallback path.
## When to Invoke
**Explicit invocation (`/convergence-monitoring`):** Standalone assessment — reads wave
history from `.orchestrator/metrics/events.jsonl`, computes all three signals, reports
verdict + recovery options.
**Embedded (loop context):** `/autoresearch` and `wave-executor` invoke this skill after
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_bsoido7vz56icjys
GET https://markdownregistry.com/api/v1/resolve?ref=lstr-1/skills/convergence-monitoring
GET https://markdownregistry.com/api/v1/blob/6027dd6a76729d33375f71c9624547fc84b90b2ef8dc0b77f4774fde106cf28c
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
lstr-1/skills · create-skill/SKILL.md · Use when the user wants to create, design, or generate a new AI agent skill (SKILL.md) from a problem description. This…
lstr-1/skills · monitor-startup-dach/SKILL.md · Fetch the top-25 posts from r/StartupDACH/hot.json, classify each into six deterministic German intent clusters…
lstr-1/skills · nlm-meta-study/SKILL.md · Create scientific meta-studies on any topic using Gemini Notebook (NotebookLM). Invoke for systematic reviews…
lstr-1/skills · orchestrator/skills/architecture/SKILL.md · Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities…
lstr-1/skills · orchestrator/skills/autopilot/SKILL.md · Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan →…
lstr-1/skills · orchestrator/skills/bootstrap/SKILL.md · Use this skill when scaffolding the minimum repository structure required by orchestrator. Invoked automatically by the…
lstr-1/skills · orchestrator/skills/brainstorm/SKILL.md · Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue…
lstr-1/skills · orchestrator/skills/claude-md-drift-check/SKILL.md · Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository…
lstr-1/skills · orchestrator/skills/daily/SKILL.md · Use this skill when creating today's daily note in the Meta-Vault (03-daily/YYYY-MM-DD.md) with valid…
lstr-1/skills · orchestrator/skills/debug/SKILL.md · Use when encountering any bug, test failure, build break, or unexpected behavior — runs a 4-phase systematic debugging…
