history-search
Skill10 starsChanged yesterdayMITView on GitHub
Search and retrieval across task history, runs, and reviews
In this repository44 other files it gives its agents.
- llms-full.txtllms.txt
- llms.txtllms.txt
- ai-prompt-engineering-safety-reviewSkill
- ast-codemapSkill
- ast-grepSkill
- autoharnessSkill
- autonomous-backlog-driverSkill
- claude-kimi-mcp-normalizationSkill
- cli-self-updaterSkill
- code-frugalitySkill
- codemode-gatewaySkill
- codemode-typesSkill
- consequence-simulationSkill
- context-pruningSkill
- github-update-checkerSkill
- google-agents-cli-evalSkill
- google-agents-cli-scaffoldSkill
- hook-gatingSkill
- hybrid-semantic-searchSkill
- kimi-code-agent-integrationSkill
- kimi-mcp-configurationSkill
- leann-vectorSkill
- log-summarizerSkill
- markdown-vagueSkill
- memory-reconciliationSkill
- mode-classificationSkill
- multiagent-orchestrationSkill
- output-compressionSkill
- prompt-injectionSkill
- python-anti-patternsSkill
- regression-sentinelSkill
- restart-trackingSkill
- rollback-guardSkill
- rust-call-graphSkill
- secrets-managementSkill
- security-best-practicesSkill
- session-compactorSkill
- sqlite-memorySkill
- swarm-barrierSkill
- swarm-dagSkill
- autoharnessSkill
- code-reliability-checksSkill
- skill-threat-rulesSkill
- autoharnessSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use when querying previous execution details in long-running tasks without loading massive logs into active context:
- Very specific: line 16
Call harness_history_search(query, kind) where kind is runs, reviews, or all.
- Distinctive: line 20
If a specific test error needs full inspection, fetch only that run's snippet rather than the entire 500-line pytest dump.
- Very specific: line 25
Run harness_history_search with an assertion query and verify matched log snippets are returned.
- Very specific: line 26
Verify filtering by kind (runs vs reviews) returns only relevant records.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
history-search
When to use
Use when querying previous execution details in long-running tasks without loading massive logs into active context:
- Searching past test logs (
runs/*.log) for specific assertion failures or stack traces. - Querying earlier critic reviews and arbitrator decisions.
- Retrieving previous tool call outputs on demand.
Steps
- Targeted query dispatch:
- Call
harness_history_search(query, kind)wherekindisruns,reviews, orall. - The search engine inspects task log files on disk and returns only matching lines with file coordinates and line numbers.
- Reference: Reversible context retrieval (https://github.com/ranxianglei/billion-context).
- Call
- Context decompression:
- If a specific test error needs full inspection, fetch only that run's snippet rather than the entire 500-line pytest dump.
- Bounded token return:
- Limit search results to the top matching snippets with context windows (e.g., 3 lines before/after).
How to verify
- Run
harness_history_searchwith an assertion query and verify matched log snippets are returned. - Verify filtering by kind (
runsvsreviews) returns only relevant records.
Facts found here
runs/directory in task state holds output of everyautoharness verify run.answers/directory holds exact responses of critic and quality reviewers.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

