pfBlockerNG

Triage a GitHub issue end-to-end: read it whole, decide whether the report actually checks out, assess its impact, and produce an ordered RESOLUTION PLAN whose every step carries the brief notes for a delegate sub-agent. Args: <issue-number> [--fix]. Without --fix it stops at the plan (triage verdict + impact + per-step brief notes). With --fix it also EXECUTES the plan: all work happens in ONE dedicated git worktree on branch `issue/{NN}-{slug}` reused across every step, each step is run by a fresh sub-agent briefed with that step's prompt + CLAUDE.md + the previous step's handoff, you (the orchestrator) gate and independently verify each agent's output before the next starts, and each agent returns a handoff document you pass to the next. Lands the fix via /pr-merge-flow. Use when the user says "triage issue N", "look at issue N", "/gh-issue N", "investigate and fix issue N", or invokes /gh-issue.

Land a PR end-to-end the repo's DEFAULT way: review feedback first, then merge. Roughly `/pr-comments N --wait-for=coderabbitai && /pr-merge N` — get the review feedback, validate + apply each finding and reply, and ONLY if that completes cleanly, rebase the head onto the live base, wait for the real CI to go green (EXCLUDING the bot), merge `--rebase` (never a merge commit, never squash) and delete the branch. The review step ALWAYS runs the committed `review-single` workflow — ONE Claude sub-agent as an ADVERSARIAL reviewer IN ADDITION TO CodeRabbit, never a mere fallback — at reasoning effort xhigh (never below, never max): the latest Sonnet (5 or newer) — Fable (5 or newer), preferred for a large/complex PR, is temporarily unavailable, so use Sonnet (never Opus, never a multi-agent fan-out). In parallel it gives CodeRabbit ~10 minutes to acknowledge the PR: if it does, wait on its review too; if it stays silent, nudge it once with `@coderabbitai review` and wait 10 more minutes; if it is STILL silent the

Land a pull request the repo's way: rebase its head branch onto the target branch, push, wait for CI to go green (EXCLUDING CodeRabbit — never block on the bot), then merge with `--rebase` (never a merge commit, never squash) and delete the remote branch. Refuses to merge a draft, a conflicting/unmergeable PR, or one whose CI is red. Args: [PR number] (defaults to the current branch's PR). Use when the user says "merge this PR", "land PR N", "rebase and merge", "merge it once CI passes", or invokes /pr-merge. Companion to /pr-comments — handle review feedback first, then /pr-merge.

Interactively design and author a NEW ADR (Architecture Decision Record) for this repository, then write it to .ADRs/ADR_NN_Name/ as ADR.md plus ordered phase-prompt .txt files ready for /adr-phase. Args: [optional one-line topic]. Use when the user says "create an ADR", "start a new ADR", "let's design ADR-N", or invokes /adr-create. You act as a skeptical design partner, not a transcriber.

Implement an ADR (Architecture Decision Record) — a single phase, or the whole ADR end-to-end with the `all` selector. Args: <ADR-number> <phase-number | all> [--base <branch>]. Runs in a dedicated per-ADR git worktree (your main checkout stays free); each phase is executed by a fresh sub-agent with a clean context — briefed with the phase prompt, CLAUDE.md, and the prior phase's handoff, working in the full worktree. Commits AND pushes branch `adr/{NN}-{slug}` after every phase (crash-safe), so the run is resumable — on restart it resets to the last completed phase and continues. When the ADR is complete it offers a PR (default) or a rebase onto the base. Use when the user says "implement phase N of ADR-M", "run adr phase", "implement all of ADR-N", "finish ADR-N", or invokes /adr-phase.

Run ONE ad-hoc coding task through the full CLAUDE.md delegation contract — the same brief → Sonnet 5 implementer → mechanical gate discipline /adr-phase and /gh-issue enforce, for work that belongs to neither. Args: <task description> [--base <branch>]. Use when the user says "delegate this", "have sonnet build X", "do this via the contract", or invokes /delegate. Not for ADR phases (/adr-phase) or issue fixes (/gh-issue --fix) — route those to their skills.

Retrieve a pull request's review comments — CodeRabbit's inline findings PLUS its nitpick and outside-diff-range findings (and human reviewer comments) — validate each against the CURRENT code, apply the ones that genuinely hold (skip the rest with a reason, defer pre-existing ones to their own PR), then reply on every thread. Nitpick AND outside-diff-range findings are mandatory to handle, with the same rigor as inline ones — every finding gets a verdict and a reply; none is skipped merely for the bucket it landed in. With --wait-for=<handle> it first blocks until that reviewer (usually CodeRabbit) has FINISHED reviewing — polling the PR, not a one-shot read — and, if CodeRabbit declines because the base isn't the default branch, comments to trigger a full review and keeps waiting. --wait-for is repeatable / comma-separated (e.g. --wait-for=coderabbitai,snyk) to wait on several reviewers, skipping any that are not reviewing the PR. Args: [PR number] [--wait-for=<handle>[,<handle>...]] (PR defaults to the cur

Lint ADR phase prompts for the delegation-contract blocks (VERIFICATION, HANDOFF naming its RESULTS file, declared test mode, reality-override line, blast-radius line from ADR-62 on) via scripts/check_phase_prompts.py — the mechanical floor beneath /adr-create. Args: [ADR number or prompt file paths] (default: every tracked post-contract prompt). Use when the user says "lint the ADR prompts", "spec-lint ADR N", "check the phase prompts", or invokes /spec-lint. /adr-create runs this before reporting a new ADR done.

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

Structured hypothesis-ledger debugging (CLAUDE.md "Evidence rules"): reproduce first, list competing hypotheses, run the discriminating probe for each, and only fix a CONFIRMED cause — never "try a fix and see". Args: <symptom, error message, or failing command>. Use when the user says "debug this", "why is X failing", "investigate this error", or invokes /debug. For a filed GitHub issue, prefer /gh-issue N (it embeds this protocol).

Launch a new, detached interactive Claude Code instance that inherits THIS session's configuration directory (CLAUDE_CONFIG_DIR), starts in the same working directory, and — when the current session has remote control enabled — enables /remote-control on the new instance too. Use when the user says "new terminal", "spawn another claude", "launch a second instance", or invokes /new-terminal.

Cut a pfBlockerNG release WITH hand-authored release notes: play the role of the GitHub Models step — write docs/release-notes/<tag>.md from the commit range using the same prompt the workflow feeds the model — commit it on the channel branch, then hand off to the /release skill to validate the scheme + dispatch the release workflow (which creates+pushes the tag and publishes; no tag is pushed by hand). Because the file is committed, the workflow's GitHub Models step is skipped and the release body comes from your file. Use this when Models is unavailable (e.g. the org hasn't enabled it), when you want curated notes, or when the user says "write the changelog and release", "release with notes", "play the model and cut the release", or invokes /release-with-changelog. Args: <tag> (e.g. v4.0.0.alpha.1).

Cut a pfBlockerNG release by validating the tag scheme, then DISPATCHING .github/workflows/release.yml — the workflow itself creates+pushes the tag and publishes (GitHub Release + .pkg artifacts + self-hosted pkg-repo publish + FreeBSD-ports bump). You do NOT push a tag by hand. Enforces the scheme before dispatch: prereleases (vX.Y.Z.alpha.N | .beta.N | .rc.N) cut from `devel` only, stable (vX.Y.Z) from `main` only — the same rule release-version.sh, the workflow's prepare-release job, and the pre-push hook enforce, so a bad tag is refused locally instead of failing in CI. Args: <tag> (e.g. v4.0.0.alpha.1) [--dry-run]. Use when the user says "cut a release", "release vX.Y.Z…", "tag a release", "publish the alpha", or invokes /release.

Shortcut for `/adr-phase <ADR-number> all` — implement an entire ADR end-to-end. Same parameters as /adr-phase minus the phase selector. Args: <ADR-number> [--base <branch>]. Use when the user says "implement all of ADR-N", "run the whole ADR", "finish ADR-N", or invokes /adr-all.

List the ADRs that are still open work — NOT yet implemented and NOT already in flight — as a table of `ADR-NN | Name | Status`, so you can pick what to build next. "Not implemented" = the ADR's code has NOT landed on `devel` AND it has NO open PR. Excludes Rejected ADRs, anything already Accepted/landed, and anything with an open PR. Read-only; writes nothing. Args: none. Use when the user says "list ADRs", "what ADRs are left", "which ADRs can I work on next", "adr-list", or invokes /adr-list.