output-compression
Skill10 starsChanged todayMITView on GitHub
Intelligent cascading output compression for test, diff, build and log streams
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
- history-searchSkill
- hook-gatingSkill
- hybrid-semantic-searchSkill
- kimi-code-agent-integrationSkill
- kimi-mcp-configurationSkill
- leann-vectorSkill
- log-summarizerSkill
- markdown-vagueSkill
- memory-reconciliationSkill
- mode-classificationSkill
- multiagent-orchestrationSkill
- 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
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use whenever tool or command execution output (pytest, compiler, test runner, git diff, npm/cargo) produces hundreds or thousands of lines …
- Very specific: line 28
Verify harness_compress_output in Gateway MCP.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
output-compression
When to use
Use whenever tool or command execution output (pytest, compiler, test runner, git diff, npm/cargo) produces hundreds or thousands of lines that would pollute the agent's context window. Grounded in dean0x/skim, this skill compresses raw logs by 70-95% while isolating critical failures.
Steps
- Identify Log Stream Format:
Detect whether the input stream is
pytest,unittest,git_diff,traceback, orcompiler. - Skeleton & Failure Extraction:
- For test suites: fold passing dots (
...), retain failed test names, exception types, and traceback lines. - For git diffs: summarize file changes, fold long context lines, keep active diff hunks.
- For compiler/build logs: filter for
error:andwarning:lines with file coordinates.
- For test suites: fold passing dots (
- Compute Compression Metrics:
- Measure original characters/lines vs compressed characters/lines.
- Calculate compression ratio:
1.0 - (compressed_len / raw_len).
- Deliver Cascading Representation:
- Save full uncompressed log to persistent storage (
.autoharness/runs/...or scratch). - Return clean folded skeleton to agent / user with compression stats.
- Save full uncompressed log to persistent storage (
How to verify
- Run
pytest tests/test_output_compression.py. - Execute
autoharness skim <file_or_command>and check compression ratio. - Verify
harness_compress_outputin Gateway MCP.
Facts found here
- Compressing test and build output typically achieves 75-92% token reduction, preserving critical context without blowing up model prompt limits.
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.

