AGENTS.md instructions for adityaarakeri/senior-agent-skills: This project carries a set of engineering playbooks under skills/. In this harness they are not loaded automatically, so this table is the trigger list: when the current phase matches a row, open that file and follow it before doing the work.
Thoroughly find dead, unused, and unreachable code in a repository and produce a confidence-ranked report. Use this skill whenever the user asks to find dead code, unused variables, unused functions or classes, unreachable code, orphaned files, unused exports, unused dependencies, stale CI files, orphaned config…
Diagnose bugs, failing tests, crashes, regressions, flaky behavior, and performance failures when the cause is unknown. Use for stack traces, wrong output, intermittent failures, environment mismatches, or repeated unsuccessful fixes. Do not use when the root cause is already established and the task is to implement…
Evaluate changes to prompts, model or provider versions, RAG retrieval and ranking, tool schemas, agent policies, structured outputs, safety filters, and model routing. Use when AI-system quality, safety, latency, or cost may change. Do not use for ordinary deterministic code changes; use tdd-loop for those and…
Execute explicitly requested version-control mutations safely, including staging, commits, branches, merges, rebases, conflict resolution, undo operations, and pull-request preparation. Always use before force push, reset, clean, history rewrite, or deletion. Do not trigger for read-only status, diff, log, blame, or…
Produce and maintain an implementation plan for risky, ambiguous, irreversible, or coordinated changes, and whenever the user asks for a plan or approach. Trigger on public contracts, schemas, auth, payments, migrations, build or deployment systems, and material design choices. Do not use for low-risk mechanical work…
Map an unfamiliar repository, service, or module before non-trivial work. Use when entering a codebase not explored in the current session, onboarding, tracing an unknown flow, or recovering from a wrong structural assumption. Do not use for a scoped, obvious change when the relevant files, commands, and conventions…
Change internal code structure while preserving observable behavior through small verified steps. Use for renames, extractions, moves, decomposition, and duplication removal when behavior must remain stable. Do not use for bug fixes, public contract changes, dependency or framework migrations, schema migrations, or…
Review a completed diff or change set for correctness, security, regressions, scope, and missing tests. Use in author mode before handoff or in read-only mode when the user asks to review, inspect, check readiness, or report findings. Do not replace runtime completion evidence from verify-done, and do not fix findings…
Implement a known feature, behavior change, or diagnosed bug with a red-green-refactor loop. Use when the user asks to add, build, implement, or fix behavior and automated tests exist or should exist. For an unknown failure cause use debug-protocol first; for model, prompt, RAG, or agent quality use…
Gate completion claims with observed build, test, runtime, documentation, and diff evidence. Use at the end of implementation or when the user asks whether existing work is complete. Do not use as the primary code-review workflow, and do not repair failures during a verification-only request unless the user separately…
Claude Code instructions for adityaarakeri/gitatlas, covering claude.md, what this is, commands, architecture and the three rules (from contributing.md, enforced by tests).
Turn a folder of repos or any GitHub repo into one interactive HTML architecture map, from system down to function. 21 languages, fully offline, with an MCP server for coding agents. Runs locally from the gitatlas npm package.