ContextDevKit

Domain Engineering diagnostic — shows what the classifier decides for an objective (CMIS/DAS/profile/skills/mode). Observation-only; never mutates or blocks.

Business-driven methodology entry point — classify (intake), create/advance an Operation or Business work context, and drive the intake → operation → nested-workflow flow. Host-neutral; dry-run by default.

Workflow Navigator — shows the current phase, deliverables, and next commands for an ADR-0057 workflow. Read-only; never mutates state.

Start a focused session on one objective — locks scope, blocks opportunistic refactors.

Deterministic QA gate (ADR-0055) — run the project suite; green + complete acceptance criteria ⇒ qa-approve testing cards into conclusion; red ⇒ report (and qa-reject only attributable failures).

L6 — autonomous feature pipeline. Drives the full squad: design → implement → review → test → log. Checkpoints can be manual or automatic.

Swarm coordinator (ADR-0051) — pull N disjoint backlog tasks and run them as parallel, governed workstreams in isolated worktrees. Finishes at testing/; humans merge via `/swarm review`.

QA — final verdict. Run the suite, check critical-path coverage vs target, write a PASS/NEEDS-WORK report.

Codex usage and autonomy insight from ContextDevKit receipts, without reading unstable private transcript formats.

Workflow spec pack - PRD/PDR + SPEC -> ADR -> roadmap -> pipeline -> ship -> testing -> conclusion. (ADR-0057)

Manage Model Context Protocol (MCP) servers — discover, add (curated), health-check, audit, and sync host configs from the curated registry.

Ensure every app/module has its own scoped AGENTS.md, then fill each with real local rules.

Manual Codex premium reasoning tier — run one explicitly requested task on the host-resolved reasoning model, then return to normal.

One-shot intelligent onboarding — inspects the project and self-configures ContextDevKit to it.

Register the current session (creates a session file + updates CHANGELOG). Use at the end.

Quick summary of current project state (latest session + Unreleased + key rules)

Show or verify a stored Session Autonomy Receipt (token/autonomy/cost) for a session.

Context budget — guidance on WHICH context files to load per task type (always / on-demand / skip) to keep token cost low. Read-only advice. (ADR-0066)

Show/route/grow/audit the agent squads — the roster, playbooks, active routing, and onboarding config.

Open a multi-agent deliberation — a council of specialist voices debate a hard question with tiered research, a synthesizer converges, the result feeds an ADR. (ADR-0035 / ADR-0070)

Create a new ADR (Architecture Decision Record). Use BEFORE implementing a big decision.

L5 — analyze recent sessions and propose refinements to AGENTS.md (writes a proposal, applies nothing).

L6 — learning loop. Turn recurring drift/debt/patterns from recent work into concrete governance (rules + ADRs).

QA — materialize tests for the given files, routing each slice to the right specialist.

QA — generate a 3-layer test plan (happy / edge / failure) for a scope, before writing test code.

Show or set the autonomy dial — how much the AI may do without asking (consent grade 1–4, orthogonal to the capability level).

L5 — apply a reviewed .distillation-proposal.md to AGENTS.md and record an ADR for the cycle.

Fleet mode — one control plane over many ContextDevKit repos (portfolio stats, cross-repo audit, AGENTS.md rule-drift).

Re-bind the current Codex session to a previously-unregistered ledger so the in-flight narrative can be finished and properly /log-session'd. (ticket 046)

Close the predicted-vs-actual loop — fill each prediction's Actual section from the ledger.

The DevPipeline manager - production board for bugs, increments, chores and roadmap tasks (backlog -> testing -> conclusion).

Proactive Advisor — one classified, six-lane improvement scan (architecture · features · deepen · security · UX · growth), before or after a change.

Review the codebase against the best-practices rubric and propose INTELLIGENT refactors (not random splits).

One-pass health audit — runs doctor, a tech-debt sweep, and a QA status check; summarizes top actions.

Detect breaking changes to the public contract (removed/renamed exports) vs the baseline.

Global deep analysis — every scan (code, security, deps, bugs) → report → ADRs → backlog.

Dependency & supply-chain audit (security-team) — lockfile, pinning, CVEs → backlog.

Scaffold GitHub-native security (Dependabot + CodeQL + dependency-review) and sync alerts into the backlog (security-team).

SEO + AISO audit — runs the two static analysers and summarises findings. Refuse-on-SPA for landing pages. (ADR-0025)

Audit the codebase against the constitution — deterministic scan + your interpretation.