adept-agentic

Run ASOPB evaluation with credential routing, build context sync, and baseline comparison

Walk the full ADEPT Code Hygiene Quick Reference Card checklist and report PASS/FAIL/N-A for each item. Use as a final check before pushing.

Full task closure workflow -- runs test validation, session report, tracking doc updates, commit preparation, and hygiene audit in sequence. Use at the end of a development session. Pass an optional title hint as argument.

Configure Claude Code to connect to an ADEPT instance (local Docker stack or remote server). Generates .mcp.json, runs doctor check, verifies connectivity. Use when setting up or switching between ADEPT instances.

Guided workflow to deploy ADEPT on cloud infrastructure (AWS, Azure, or GCP) as a single VM or A2A mesh pair. Covers provisioning, OS prep, stack deployment, and optional A2A federation between two independently-deployed stacks.

Add a new tool to an existing MCP server following the canonical register(mcp) + Pydantic pattern. Use during Phase 4 (Implement) of the feature development lifecycle.

Analyze a Python library and produce an MCP server implementation plan. Audits the API surface, maps functions to tools, classifies dependencies, and identifies session boundaries. Use during Phase 1-2 (Plan + Discover) of the feature development lifecycle.

Register (or re-register) an MCP server's tools with the ADEPT gateway. Includes pre-flight validation, schema checking, registration, and verification. Use during Phase 9 (Close) of the feature development lifecycle.

Create a new external MCP server from the canonical template. Replaces placeholders, assigns ports, validates the result. Use during Phase 4 (Implement) of the feature development lifecycle.

Run the 4-tier test strategy for an MCP server (unit, integration, registration, E2E). Use during Phase 5 (Test) of the feature development lifecycle.

Semantic self-review of staged/committed changes before push. Runs 5 targeted audits to catch pattern inconsistency, dead code, doc-code divergence, Helm template logic gaps, and unreachable code paths. Reduces Copilot review from 4+ rounds to 0-1.

Build a Conventional Commit message with Related Documentation footer chains. Use after all docs are updated, when ready to commit.

Create a pull request, check Copilot/peer review status, address findings, resolve review conversations on GitHub, and verify review clearance. Use after committing and pushing, as part of Phase 9 (Close). Pass optional PR number as argument to check an existing PR.

Before publish — ASOPB scan, staging, dry-run, publish gate (NEVER executes publish)

Check promptfoo LLM red-team credentials availability and offer to run Pass 5 adversarial scan against a live endpoint.

Assess and address PR review findings from Copilot, CodeRabbit, or human reviewers — classify, fix, reply, resolve

Run ASOPB security scan on an arbitrary directory and report findings with ASPI score

Run ASOPB scan on staged release tree and report findings with ASPI score

Submit arbitrary Slurm HPC jobs via ADEPT agent — supports single-agent (v1) and multi-agent (v2 with LLM-as-judge) execution modes. Handles script hardening, mode selection, and result verification.

Walk through the full ADEPT feature development lifecycle (Phase 0-9). Invokes sub-skills at each gate. Use at the START of any new feature, bugfix, enhancement, or refactoring work. Pass optional work type as argument (feature, bugfix, refactor, chore).

Initialize a new sprint with GitHub issue parity, local tracker updates, and a testing/deployment strategy. Creates umbrella + sub-task issues, updates all local tracking docs, and defines validation requirements per sub-task and for the umbrella. Use at the START of a new sprint or workstream.

Check documentation parity across public Pages, internal wiki, CLAUDE.md/CLAUDE.public.md, and skill registry — detects drift, stale content, safety violations, and missing skill entries

Investigate and triage CVEs from Grype/TruffleHog scan findings — lookup, reachability, remediation

Update CHANGELOG.md, ROADMAP.md, and KNOWN_ISSUES.md with entries for the current session. Use after the session report is written, before committing.

Check that all required test tiers have been run for the current changes. Use after making code changes and before committing.

Generate a session implementation report or bugfix document following ADEPT conventions. Use after tests pass, before committing. Pass an optional title hint as argument.