AI Agent Workflow Collection

Fork/plugin-consumer entrypoint for the intention-graph harness — on-demand, /align-init orients the practitioner (virtues, strategies, tactics, delegations), validates the tooling deployment, reviews inherited virtue roots via the Socratic rung-0 interview, and hands off to /align-strategy; the scheduled (align jit) trigger runs the rung-5 dialectic engine unchanged (structural roles drive the dialectic, perspectives feed it — it synthesizes priorities, a contrarian challenges, it re-synthesizes, triages the backlog, and produces roadmap recommendations plus per-priority delegability findings) and posts a report that closes the review issue.

Interview-driven recording of a strategy- intention node — the graph-native successor to /file-issue's requirements-definition role. Frames the input as a new strategy or an edit to an existing one, runs a Socratic dialectic to fix intent/placement/benefit/signal/conditions, advises on delegation capture, retains tactical byproducts as draft tactic nodes, and lands the record via graph-commit. On-demand only; never files a GitHub issue.

Autonomously break a recorded strategy- intention node into PR-sized tactic subtrees carrying full clean-session plans — the graph-native successor to /plan-issue and /file-issue's epic-structuring role. Two-sided drift review, decompose to the signal, plan each claude-eligible tactic into its node body, park the rest; lands via graph-commit. Never files a GitHub issue; never AskUserQuestion mid-run.

Monthly QFX merge workflow — identifies bank statements, generates an inspection report, iterates on categorization rule patches, and writes an encrypted budget snapshot.

Parse-job handler for the dispatch chain — runs budget-etl from a statement parse-job issue (filed by dispatch-statements-scan), report-first to detect uncategorized transactions, then idempotently merges the statement into the user's encrypted .benc snapshot in place, closes the issue, and writes the parse-job-done sentinel; escalates to office-hours when categorization needs the author.

Guide a user through adding a new bank-statement parser to budget-etl for an unsupported export format. Trigger when the user runs /budget-parser .

Fork subagent that commits pending changes in logical units, merges origin/main, and pushes to origin HEAD.

Autonomous worker lane that drafts broader-context reading chunks (passages + questions only) deepening a resolved reading. Trigger on /context-chunks ; Opus-only; born-parked drafts, never phase-set tactics or tradition records.

Fix-conflicts phase — single pass that reproduces and resolves one conflict on three lanes (Lane 1, an origin/main merge conflict on an issue-branch draft PR; Lane 2, a graph-native intention-node conflict parked by graph-commit; Lane 3, an origin/main merge conflict on a graph node's own branch, entered by source id or by the id of the provision-conflict hold tracking it), or escalates an ambiguous conflict to…

Diagnose origin/main's failing CI when /dispatch-propagate detects a red main; runs as a spawned bg job that enumerates failing checks, fetches logs, and files the redacted likely-cause summary as a find-or-create dispatch:main-broken issue.

The invalid-state lane's intervention session for a node held by a terminal, undeclared worker — reads the dead session's transcript, files a find-or-create root-cause follow-up, then completes a verified missed disposition, reaps, or parks to office-hours. Spawned by dispatch-invalid-state-route; never invoked on a live claim.

Claim the earliest-due JIT issue, then either run a configured skill (for skill-running jits such as digest) or summarize it for the user and stop. Runs as a spawned bg job from /dispatch-propagate when the JIT scan surfaces a due reminder.

Retired: the autonomous dispatch tick is now the headless dispatch-tick script (launched by dispatch-spawn-tick); see the dispatch terminal command for the manual entry point.

Audit recent dispatch session transcripts and emit a ranked report of token-reduction opportunities across nine lenses, ranked by measured price-proxy magnitude. Primarily report-only; also writes the phase-model routing policy artifact. Accepts an optional window, e.g. /dispatch-token-audit 2d.

File a new vibix GitHub issue with the correct priority/area/track labels applied up front. Use whenever an agent needs to capture a new unit of work — follow-ups from a merged PR, TODOs discovered while coding, or manually-requested issues. Invoked as /file-issue.

Fix-checks phase — single pass that reproduces and fixes one set of failed CI checks on a draft…

Fix-conflicts phase — single pass that reproduces and resolves one origin/main merge conflict on a draft PR, or escalates an ambiguous conflict to…

Interactive author-invoked grounding-research skill — the author-side consumer of the tick gap analysis. Walk the ranked unmarked durable-layer nodes top-down; per node, mark it circumstantial or /deep-research frontier work into candidate curriculum chunks; land every mark and new chunk in one graph-commit. Office-hours only, never tick-invoked.

Implement one planned unit of work in a subagent, then commit, merge, and push it with error…

Invoke when the user introduces a new requirement or changes a previous understanding of a requirement — clarifies, updates remote issues, and revises the active plan.

Plan phase — autonomously plan a no-PR issue into an ordered unit breakdown via the built-in Explore/Plan subagents, persist the plan to the issue, and apply dispatch:planned (no user gate; escalates to office-hours only on genuine…

QA phase — merge origin/main, run the autonomous portion of user-acceptance QA (plan items, machine-verifiable checks, PR-comment summary), apply the dispatch:qa-done label on a clean pass, run the bounded Opus auto-fix lane on opus-fixable residue (per-unit /implement-unit, re-QA via the chain, attempt-capped), and escalate to office-hours on any user-input…

autonomous main-qa handler — verifies a no-PR needs-main follow-up against deployed main/prod via Claude-in-Chrome; pass → close, broken → file implement-chain bug + close, cannot-verify → escalate to office-hours; the autonomous counterpart of the office-hours human main-qa review.

Office-hours skill that runs one tradition-reading curriculum chunk's demonstration — the author demonstrates understanding of the tradition and its application to the deferral against the primary text, the graph is amended where the reading contradicts it or ratified where it holds, and the chunk node is resolved (phase → done), which triggers /sync-reader's retirement of the chunk's excerpt from the e-reader. Interactive and unbounded; the inverse of /align-tactics' autonomy contract. Never files a GitHub issue.