A spec-driven pipeline that makes building with AI fast, accountable, and cumulative.
This repository also configures its own agents. See what adlc-toolkit tells them →
Skill Claude CodeCodex
Standalone codebase health audit. Dispatches the health-auditor agent and produces a dated report in .adlc/audits/. No pipeline state, no gates — read-only audit that you run periodically or on demand.
Skill Claude CodeCodex
Design the architecture and task breakdown for a REQ. Phase 2 of /proceed. Dispatches codebase-explorer to inform the design, then drafts architecture.md and tasks/TASK-.md. On high-stakes REQs, dispatches the architecture-adversary to attack the design before the gate so the user reviews a stress-tested plan. Ends in…
Skill Claude CodeCodex
Autonomous end-to-end pipeline. Runs /spec → /architect → /implement → /review → /wrapup like /proceed, but instead of pausing at each gate it routes the decision through the decision-maker agent, commits its work as it goes, and ends in a single final human review backed by a full audit log. Opt-in; conservative by…
Skill Claude CodeCodex
Streamlined pipeline for bug fixes. Slimmer than /proceed — bug report → investigate → fix → verify → ship, with gates between each. Use for defects, not for new features. Larger or scope-creeping bugs should be re-framed as a REQ via /spec.
Skill Claude CodeCodex
View and change ADLC project settings in .adlc/config.yml — git policy, isolation, how freely the assistant may edit, external sources, autonomy levels, stack, protected branches, repos — through guided options, then re-sync any derived files. Also migrates an existing vault's config to pick up new keys after a…
Skill Claude CodeCodex
Execute the task DAG for a REQ. Phase 3 of /proceed. Dispatches task-implementer agents (tier-based parallel where possible), drafts commit messages to commits-draft.md, runs tests, then ends in the implement gate.
Skill Claude CodeCodex
Bootstrap the .adlc/ vault in a new repo — copies templates, generates the CLAUDE.md schema doc, creates empty vault files (now, hot, index, decisions, glossary, gotchas), and scans for existing documentation (README, ARCHITECTURE, CONTRIBUTING, lint configs, prior ADRs, GLOSSARY) to seed context/ and architecture/…
Skill Claude CodeCodex
Standalone performance and cost audit. Dispatches the performance-scanner agent and produces a dated report in .adlc/audits/. Identifies LLM/API cost hotspots, DB performance issues, latency drivers, caching opportunities. No gates — read-only.
Skill Claude CodeCodex
End-to-end pipeline orchestrator. Runs /spec → /architect → /implement → /review → /wrapup in sequence with gate-pause between every phase. Resumable from any phase via pipeline-state.json. Use this when you want the full pipeline rather than invoking each phase skill separately.
Skill Claude CodeCodex
Reconcile pipeline-state.json against git reality for one, several, or all in-flight REQs and bugs. Diagnoses each as in-sync, stale-state, abandoned, sprint-stuck, or divergent, then surfaces a triage queue and back-fills the vault for REQs whose code shipped without /wrapup running. Read-only on code and git…
Skill Claude CodeCodex
Multi-perspective code review for a REQ. Phase 4 of /proceed. Dispatches 4 read-only review agents in parallel (correctness, quality, architecture, reflector) — plus a 5th ui-reviewer that runs the app in a browser when the change touches a UI surface — consolidates findings by severity, and ends in the verify gate.
Skill Claude CodeCodex
Parallel multi-REQ orchestrator. Launches one pipeline-runner agent per REQ in an isolated worktree. Each runner pauses at its first gate; the orchestrator maintains a unified queue of waiting gates across all REQs. Who clears that queue follows the autonomy.gates dial — the user (manual, default), the user with a…
Skill Claude CodeCodex
Read-only overview of all active work — REQs in flight, current phases, gate states, blockers, recent activity from hot.md. Use to orient at session start or to triage when /sprint has multiple REQs in flight.
Skill Claude CodeCodex
Slim ADLC pipeline for small changes — a tweak, a small feature, a contained refactor that's too small for /proceed's five phases but should still live in the vault. Triage → plan (gate) → implement → review + ship (gate). Self-triaging: recommends /proceed if the work is actually large, up front or mid-flight…
Skill Claude CodeCodex
Update the ADLC toolkit install itself from upstream and reconcile every tool's adapters. Pulls new core/ engine changes, re-runs the installer (safe to run repeatedly; new skills linked, removed ones cleaned up), and — crucially — flags where a file you customized in local/ overrides a core file that upstream just…
Skill Claude CodeCodex
Standalone UX & design-system audit of the whole app or a chosen part of it. Sizes the UI surface first — small apps get one pass; large apps get a gated segment plan run in phases (system pass → per-segment passes → cross-segment consolidation) with durable progress that survives sessions (/ux-doctor resume).…
Skill Claude CodeCodex
Final phase of /proceed. Drafts the PR (title, body, change summary), updates the vault (lessons, gotchas, index, hot, decisions, concepts, components), and prints the git/gh checklist for the user to run. Claude does NOT commit, push, PR, or merge.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: