agent-tool-call-latency
Measures every agent tool call on this machine from local session history (the user's chat logs), in any harness, finds where the time goes, and ranks fixes for slow commands, harness overhead and wasted waiting. Use when the user asks why their agents are slow, where agent run time goes, or how to cut the time agents spend waiting on tools.
- License
- Apache-2.0
Pinned to revision fe059fde151b, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/agent-tool-call-latency/SKILL.md
- skills/agent-tool-call-latency/agents/openai.yaml
- skills/agent-tool-call-latency/references/ADAPTERS.md
- skills/agent-tool-call-latency/references/BENCHMARK.md
- skills/agent-tool-call-latency/references/CAUSES.md
- skills/agent-tool-call-latency/references/SCHEMA.md
- skills/agent-tool-call-latency/scripts/adapters/antigravity.py
- skills/agent-tool-call-latency/scripts/adapters/claude_code.py
- skills/agent-tool-call-latency/scripts/adapters/codex.py
- skills/agent-tool-call-latency/scripts/adapters/cursor.py
- skills/agent-tool-call-latency/scripts/adapters/hooklog.py
- skills/agent-tool-call-latency/scripts/adapters/t3code.py
- skills/agent-tool-call-latency/scripts/aggregate.py
- skills/agent-tool-call-latency/scripts/common.py
- skills/agent-tool-call-latency/scripts/extract.py
- skills/agent-tool-call-latency/scripts/hook_capture.py
- skills/agent-tool-call-latency/scripts/validate_calls.py
- skills/agent-tool-call-latency/tests/test_scripts.py
Every link opens the file at its source, pinned to the revision this page describes.