awa-bundled

Set up a scheduled headless afk run that pushes a summary to Telegram. Use when the user wants to automate a recurring task via the afk daemon scheduler (cron) with push-notified results.

Reference convention for sub-agent I/O schemas. Loaded by orchestrator skills via /contract and into agents via the `skills:` field.

Adversarially critique a proposal by generating alternatives. Dispatches 3 parallel critics (pragmatist, paranoid, architect lenses) — each invents one alternative approach — then a synthesis step ranks all 4 options and recommends the top choice. When the proposal was authored by someone other than the agent (inherited plan, someone else's PR, external review), a 4th steelman critic runs in the same parallel wave and strengthens the original first, so it is judged at its strongest rather than its weakest. Use when a plan, fix, scoping, decomposition, or named recommendation will drive decisions and you want structured alternative-generation before committing. Complements /shadow-verify — that skill re-derives factual claims; this one critiques whether the chosen approach itself is best.

Parallel root-cause analysis for bugs and failing tests. Use when a test fails, a bug is reported, or behavior is unexplained — dispatches sub-agents to form and validate hypotheses in isolated worktrees.

Fires when a state-mutating task is about to be declared Done (success summary or completion verdict) — to catch silent success, the highest-frequency invisible agent failure where confident 'done' language hides work that never landed. Decomposes the completion into receipt-checkable assertions, then dispatches a reconciliation auditor that cross-references each claim against the session's tool-call LEDGER (did the producing action fire?) and a fresh postcondition READ-BACK of the named artifact (does the file/test/commit exist and match?), gating the Done behind a BACKED/UNBACKED/UNVERIFIABLE verdict plus a bounded repair loop. Distinct from shadow-verify, which RE-DERIVES an investigation finding's correctness — this reconciles a COMPLETION against execution receipts, never re-deriving the claim. Use before any Done/success in implementation, fix, refactor, migration, or multi-file write work. Skip text-terminal sessions (explanation, Q&A) and work that already failed loudly.

One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies, and issue-level conversation comments) and failing CI checks, triage each issue via parallel read-only probes, fix the validated items in an isolated managed worktree via a budget-bounded subagent, verify with the project's test gates, and push the fix back to the PR branch. Replaces the retyped recipe 'send a subagent in a worktree to fix <PR feedback>, then push.' Use when a PR has review comments or red CI that needs addressing — e.g. 'fix pr 286', 'address the review on #215', 'CI is red on the worktree-sweep PR'. Never force-pushes, never touches main, fails closed on missing gh auth or un-pushable fork PRs.

Parallel context-gathering for a code area. Use when you need to understand a module, feature, or subsystem and would otherwise read 3+ files sequentially — dispatches two agents in parallel to map structure and test coverage in one wave.

Grounds capability claims with file-read evidence. Default mode answers meta-capability questions ('what does X enable') with path:line citations. Pass mode: runtime-wiring with a claims list to trace actual runtime execution paths — call sites, DI registration, middleware — and get CONFIRMED/UNVERIFIED/REFUTED verdicts per claim. Blocks sign-off on any non-CONFIRMED claim.

Before starting any non-trivial implementation, run a pre-flight reconnaissance pass to triangulate git state, project infrastructure, and prior-session memory. Auto-assembles a verified grounding preamble — a session-scoped artifact the orchestrator pastes verbatim into every subsequent sub-agent brief — eliminating stale-worktree reads and silent wrong-path errors before the first edit.

At end-of-session, dispatches a read-only sub-agent to survey recent work and drafts a vaguely-specific priming prompt the next session can paste to orient itself and plan its next sprint. Produces orientation, not prescription — candidate directions are framed as questions, not decisions.

When finished creating the plan in plan mode, run /parallelize so Claude dispatches one planning agent to transform the current approach into a plan to orchestrate waves of parallel sub-agents.

Iteratively refines any artifact (prose, spec, prompt, API design, SKILL.md, code snippet) by running a decoupled evaluator → generator loop until explicit criteria are met or an iteration cap is reached. Locks criteria in Wave 1, isolates the evaluator from generation history to prevent sycophancy, and emits the best version with any remaining gaps flagged at cap.

Orchestrates safe, large-scale structural changes across a codebase — symbol renames, API migrations, pattern standardizations, layer restructurings. Enumerates all affected sites, groups them into dependency layers via the DAG executor, applies changes in parallel per layer with worktree isolation, and verifies behavioral preservation at each layer boundary before proceeding. Exits immediately on first regression, surfacing the exact site, diff, and behavioral delta before any commit.

Dispatches two sub-agents in parallel to gather external and local context for the current task.

Dispatches parallel dimension agents across a diff, PR (URL or number), commit SHA, branch, staged changes, or patch file — covering security, correctness, api-compat, test-coverage, and perf-observability — synthesizes findings by severity, and emits a merge recommendation. Use when changes are ready for review before merge. Read-only: this skill analyzes and reports only — it never edits files, commits, pushes, comments on a PR, or modifies the PR description.

Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap analyses) — or whenever a sub-agent asserts a claim with high-confidence language ("confident", "certain", "clearly", ≥80%), since confidence is a trigger, not a verdict. Shadow verifiers independently re-derive 2–3 key claims from scratch using tool calls only, returning CONFIRMED/REFUTED/STALE/UNVERIFIABLE, and flag disagreements before the user acts. Use when sub-agent output will drive decisions, file changes, commits, or external side-effects.

Release pipeline for already-done local work. Dispatches /ground-state pre-flight, runs the project test suite, drafts a commit message, pushes, and opens a PR with a structured verification summary. Use when local changes are ready to hand off to review — e.g. 'ship this', 'push and open a PR', 'release this work'. Add --verify to trigger an adversarial verifier wave on the diff before a human reads the PR.

Discovers incidental complexity, duplication, and dead code in a codebase and produces a ranked, behavior-preserving reduction plan — optionally applying safe changes. Dispatches four parallel read-only discovery lenses (clone detection, dead code, complexity hotspots, wrong abstraction), synthesizes into a prioritized reduction plan, and gates apply mode behind /refactor and a hard test check.

Takes a loose idea and transforms it into a structured, actionable spec ready for implementation. Use when the user passes an idea, feature request, or problem description that needs scoping before building.