log-tail
Skill1 starsChanged 45 days agoMITView on GitHub
Summarize logs and tracebacks instead of reading raw lines. Use when debugging a service, reading a noisy log file, finding recurring error patterns, or locating one event inside thousands of lines.
In this repository9 other files it gives its agents.
- commitsmithSkill
- context-budgetSkill
- gatewaySkill
- injection-guardSkill
- json-lensSkill
- repo-mapSkill
- secret-scanSkill
- tokensaverSkill
- web-snapshotSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Read the tail of any log file — plain text, JSON lines, or Python tracebacks — and get level counts, a time range, recurring patterns, and …
- Very specific: line 26
Start with tail_summary — never read raw logs first.
- Very specific: line 28
Use search_logs with a pattern from that summary to pull the exact lines and context.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Log tail
Read the tail of any log file — plain text, JSON lines, or Python tracebacks — and get level counts, a time range, recurring patterns, and grouped exceptions with stack frames.
MCP tools
| Tool | Use it for |
tail_summary | Error overview first: levels, patterns, exceptions, time range. |
search_logs | Find one event with regex and context lines. |
Workflow
- Start with
tail_summary— never read raw logs first. - Identify the dominant error pattern from the ranked list.
- Use
search_logswith a pattern from that summary to pull the exact lines and context. - Widen
linesif the window was too small, or raisebudgetfor more patterns.
CLI fallback
npx -y mcp-log-tail summary ./server.log --lines 1000
npx -y mcp-log-tail search ./server.log --pattern "timeout|refused" --context 3 --ignore-caseTips
- Lines that differ only by ids, numbers, or hex values are grouped automatically.
- The tool stays bounded: byte caps, line caps, and token budgets are enforced on every path.
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.