AI Agent & Automation Workflows

Audit agent configuration files for security vulnerabilities and misconfigurations. Covers settings.json, .mcp.json, .codex/config.toml, AGENTS.md, hooks, plugin manifests, and relay config. Classify findings as P0 or P1.

Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.

Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or…

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.

Verify that API endpoints match their OpenAPI/Swagger specifications.

Use to collapse over-engineered abstractions, remove unnecessary layers, or consolidate redundant logic.

Full autonomous execution from idea to working…

Ensure that new complex models actually outperform simple, naive baselines.

Analyze BigQuery usage, identify cost hotspots, repeated failures, and practical optimization opportunities.

Use when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.

Fix broken builds, type errors, or test failures with the smallest safe diff — no opportunistic refactors, no cleanup, no unrelated changes.

Process-first advisor routing with artifact…

Use before submitting a PR or considering a task done to evaluate the 'blast radius' of your changes.

Use when a CI pipeline fails to extract the actual error from thousands of lines of logs.

Run large codebase migrations in reviewable local batches with codemods, checkpoints, and verification. Use when a wide refactor is too risky to ship as one monolithic change.

Maintain short, focused Markdown files per subsystem to provide agents with isolated context.

Use continuously during long tasks. Teaches how to read less, output less, and keep the LLM context window lean and fast.

Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup. Stop after enough context or report what is still missing.

Audit whether a dbt incremental model uses the right incremental strategy for the repo, the data shape, and the operational constraints.

Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.

Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming conventions, no-alias SQL rule, surrogate-key and missing-record patterns, incremental strategies, deduplication, and common project macros. Use when building fact tables, dimension tables, staging models, writing SQL, or designing tests.

Use to identify and safely delete unused functions, classes, exports, and files.

Use to audit and remove unused or redundant third-party dependencies from package manifests.