Skip to main content
KurtLehnardt
GitHub creator profile

KurtLehnardt

Repository-level view of 19 collected skills across 1 GitHub repositories.

skills collected
19
repositories
1
updated
Aug 17, 2026
repository explorer

Repositories and representative skills

survive
software-developers

Wrap a worker loop so smaller or local models actually finish — response validation, rescue parsing, corrective nudges, step enforcement, and context compaction. The model proposes the next action; the harness makes the loop survivable. Trigger: make the loop…

Aug 17, 2026
observe
software-developers

Instrument an agent or LLM feature with structured spans per model and tool call, tracking the four reliability signals — P95 latency, cost per run, tool error rate, and eval pass rate — so runs can be replayed, alerted, and scored. Start with one critical…

Aug 17, 2026
sandbox
information-security-analysts

Bound an agent's blast radius with a deny-by-default sandbox policy — read allowed, writes whitelisted, egress denied — plus a per-server policy for each MCP server and violation telemetry. Contains a prompt-injected, trojaned, or rug-pulled agent; it does…

Aug 17, 2026
build
software-developers

Orchestrate a spec-driven implementation pipeline: spec intake, requirements ledger, plan, architect gate, product gate, task decomposition with model tiering, parallel ralph-loop workers, a deterministic mechanical gate plus an opus judge, and verified…

Aug 16, 2026
verdict
software-quality-assurance-analysts-and-testers

Zero-trust gatekeeper. Validates a deliverable claim-by-claim by re-running everything firsthand — refetch the diff from source, rerun the suite, re-execute the eval, rescore — never trusting the worker's say-so. Cycles work back when the letter passes but…

Aug 16, 2026
capture
software-quality-assurance-analysts-and-testers

Turn a failure — a bug, a bad output, a prod incident, a verdict FAIL — into a minimal, reproducible eval level added permanently to the suite, so the same failure can never silently return. Builds the eval flywheel. Trigger: capture this failure, add a…

Aug 16, 2026
chain-risk
computer-occupations-all-other

Compute compounding-error risk for a multi-step or multi-agent pipeline — per-step success rate raised to step count — and show where cumulative reliability falls below target, so you know where to place gates and checkpoints. Trigger: chain risk, compounding…

Aug 16, 2026
constitution
computer-occupations-all-other

Pin a north-star constitution for a multi-agent system and protect the prompt layer from tampering — detect and block unauthorized system-prompt mutation and prompt-injection that tries to redirect downstream agents. Trigger: pin the constitution, north star,…

Aug 16, 2026
Showing 8 of 19 collected skills.
Showing 1 of 1 repositories
All repositories loaded