By ntorga

Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.

ntorga/agent-starter-kit

Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.

ntorga/agent-starter-kit

Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.

ntorga/agent-starter-kit

Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.

ntorga/agent-starter-kit

Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

ntorga/agent-starter-kit

Browser inspection and interaction for verifying rendered web UI during development.

ntorga/agent-starter-kit

Reviews code and plans for logic coherence, correctness, and structural integrity.

ntorga/agent-starter-kit

Reviews code and plans against the project's coding rules. An agent skill from ntorga/agent-starter-kit.

ntorga/agent-starter-kit

How to maintain .context.md files and docs/FEATURE-MAP.md as the project evolves.

ntorga/agent-starter-kit

Assembles sub-agent prompts with task brief and routes to the correct provider.

ntorga/agent-starter-kit

Protocol that interviews the user in rounds over the Architect's design tree.

ntorga/agent-starter-kit

Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.

ntorga/agent-starter-kit

Two-mode review loop — single reviewer per epic, three reviewers for full branch.

ntorga/agent-starter-kit

Adversarial plan review — structural validation and assumption attack on grill artifacts before implementation begins.

ntorga/agent-starter-kit

File-based to-do tracking for multi-step and multi-session work.

ntorga/agent-starter-kit

Web search and page fetch through the TinyFish CLI. An agent skill from ntorga/agent-starter-kit.

ntorga/agent-starter-kit

Structured review summary format with verdict logic and coverage scoring.

ntorga/agent-starter-kit

Deterministic self-evaluation rubric for Coder — scored every run using the GRASP framework.

ntorga/agent-starter-kit

Deterministic self-evaluation rubric for Contextualizer — scored every run using the TRACE framework.

ntorga/agent-starter-kit

Structured recovery and escalation when an agent hits a retry loop.

ntorga/agent-starter-kit

Deterministic self-evaluation rubric for Reviewer — scored every run using the SHIELD framework.

ntorga/agent-starter-kit