Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/convergence-monitoring
Detecting whether agent iterations are converging toward a stable solution or hitting a ceiling. Covers convergence signals, ceiling detection, non-convergence diagnosis, test pass rate as a convergence metric, and forward progress tracking for large projects. Trigger phrases: "convergence", "is the agent converging", "ceiling detection", "when to stop iterating", "diminishing returns"
Passed 15 of 18 test cases with the skill, and 4 of 18 without it.
and 10 more in the full report
14 fixed5 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
When a convergence verdict is finalized, where is the checkpoint event record written and what is its event type key?
| Checked | Without skill | With skill |
|---|---|---|
| Appends record to path .orchestrator/metrics/events.jsonl | Missed | Passed |
| Sets event_type to convergence.checkpoint | Missed | Passed |
The instructions your model reads when the skill loads.
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/. Seeskills/_shared/platform-tools.md.
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.
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
each Impl-Core or Impl-Polish wave when convergence-monitoring: true is set in Session
Config. The skill returns a structured verdict that the caller uses to gate the next wave.
NOT a substitute for quality gates. Quality-gates verify correctness (typecheck, test, lint). Convergence-monitoring verifies progress direction — whether the work is moving toward done or oscillating/stalling.
If invoked via /convergence-monitoring, skip to Phase 1 unconditionally.
When called from wave-executor or /autoresearch, check:
skills/_shared/config-reading.md. Store as $CONFIG.$CONFIG."convergence-monitoring". If the field is absent or false, returntest cases passed, vs 4 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.