History Explorer
Agent Buildinghistory-explorerHistory Explorer is an Agent Skill for agent building published in the opensquilla/opensquilla repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/opensquilla/opensquilla/blob/HEAD/src/opensquilla/skills/bundled/history-explorer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/history-explorer, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
History Explorer
Lightweight read-only view over ~/.opensquilla/logs/decisions-*.jsonl. Aggregates DecisionEntry.skills_invoked (SCHEMA_VERSION 10) into co-occurrence frequencies, joins with SkillLoader.list_meta_specs() for meta-skill usage stats, and surfaces the tests/test_skills/router_fixtures/ corpus.
Usage
uv run python {baseDir}/scripts/explore.py \
--log-dir ~/.opensquilla/logs \
--query "Co-occurring chains for PDF workflows" \
--window-days 30 \
--include co_occurrences,meta_usage,router_fixtures \
--top-k 10
Output
JSON to stdout with keys co_occurrences, meta_usage, router_fixtures, and a placeholder string when the log is empty.
Fallback
If no decision-log exists, return an empty result with a placeholder string explaining "no history; downstream should rely on user intent only".