lrhodin/llm-pipe
skills/llm-pipe/SKILL.md
Shell primitive that pipes stdin through an LLM. Zero-cost via pi's OAuth. Use it to keep your context clean — pipe tool output through it instead of reading raw output yourself.
$ install --global
skillsauthnpx skillsauth add lrhodin/snorrio llm-pipeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 2:51 AM17.1s2 files scanned
SKILL.md
- name:
- llm-pipe
- description:
- Shell primitive that pipes stdin through an LLM. Zero-cost via pi's OAuth. Use it to keep your context clean — pipe tool output through it instead of reading raw output yourself.
LLM Pipe
llm "prompt" — pipes stdin through Claude, writes result to stdout.
Usage
# Basic — pipe anything through an LLM
cmd | llm "summarize this"
llm "what day is it"
# Trusted mode — skip injection detection for your own code/files
cat source.py | llm -t "explain this"
git diff | llm -t "one sentence summary"
# Model override
llm "prompt" sonnet
llm "prompt" claude-sonnet-4-6
Flags
-t/--trusted: skip injection detection for trusted input (your own code, git diffs, known files)
Models
Default is whatever's configured in ~/snorrio/config/config.json. Don't override it. Override with second argument only if the user asks:
haiku,sonnet,opus— aliasesprovider/model-id— explicit
CLI Setup
llm is on PATH (~/.local/bin/llm). Always use it directly — never run the source file.
Context discipline
Use llm aggressively to keep agent context clean. Every snapshot, log, diff, or command output is a candidate:
agent-browser snapshot -c | llm "list article titles and URLs"
git log --oneline -20 | llm "what changed this week"
cat log.txt | llm "anything wrong? one word"
Related Skills
lrhodin/handoff
documentation
VerifiedTrustedCommunity
Write a handoff prompt when approaching context limits or ending a session that needs continuation.
1SKILL.mdUpdated May 14, 2026
lrhodin/subagent
development
VerifiedTrustedCommunity
Spawn pi subagents in tmux for tasks that benefit from isolation — research, exploration, builds, or parallel work. Keeps your context clean.
1SKILL.mdUpdated Apr 23, 2026
lrhodin/snorrio
tools
VerifiedTrustedCommunity
This skill should be used when the user mentions snorrio, memory, recall, remembering past sessions, or when you detect snorrio is installed but not fully configured. Covers what snorrio is, setup, and first-session onboarding.
1SKILL.mdUpdated Apr 23, 2026
lrhodin/recall
databases
VerifiedTrustedCommunity
Query past sessions and temporal summaries by reviving them with full context.
1SKILL.mdUpdated Apr 23, 2026