cisco-foundation-ai

11 mods across 1 repository, 106 stars between them.

k8s-manager

01

cisco-foundation-ai/fully-automated-prompt-optimization

Agent Claude Code

Autonomous K8s namespace operator — inspects resources, tracks usage, cleans up stale pods, and launches workloads. TRIGGER when: K8s resource status, cleanup, launching workloads, pod health, resource usage, namespace overview. DO NOT TRIGGER when: running evals (use eval-runner), prompt optimization (use…

106 4d ago A 83 tokens original Apache-2.0

optimization

02

cisco-foundation-ai/fully-automated-prompt-optimization

Agent Claude Code

Optimize eval scores across all granularities: prompt text, chain parameters, and chain structure. TRIGGER when: user wants to improve prompts, analyze eval failures, iterate on prompt quality, optimize prompt variants, fix failing eval checks, do prompt engineering, optimize chain architecture, adjust retrieval/model…

106 4d ago A 127 tokens original Apache-2.0

pr-lifecycle

03

cisco-foundation-ai/fully-automated-prompt-optimization

Agent Claude Code

Full PR lifecycle agent — creates, self-reviews, simplifies, addresses review comments, and loops until the PR is ready for merge. TRIGGER when: user wants to create a PR, review a PR, address PR comments, simplify a PR, make a PR mergeable, or prepare a branch for merge. DO NOT TRIGGER when: user wants to run evals…

106 4d ago A 99 tokens original Apache-2.0

step-attribution

04

cisco-foundation-ai/fully-automated-prompt-optimization

Agent Claude Code

Post-eval failure analysis subagent. Partitions failures by optimization level (prompt vs structural) using rule-based heuristics and LLM-based deep analysis. Internal subagent — invoked by the optimization orchestrator after each eval run.

106 4d ago A 50 tokens original Apache-2.0

variant-reviewer

05

cisco-foundation-ai/fully-automated-prompt-optimization

Agent Claude Code

Independent review of a proposed prompt or chain variant against tenant context. Catches guardrail violations the optimization agent might miss (example leakage, placeholder drift, format mismatch, state protocol violations, import safety issues). Internal subagent — invoked by the optimization orchestrator, not…

106 4d ago A 61 tokens original Apache-2.0