JRichlen/agent-plugins

Before writing a new interface (module boundary, class API, function signature, or service contract) that at least two call sites will depend on, that crosses a module/service/team/persistence boundary, or that will be expensive to change later — produce 3+ radically different candidate designs and compare them on depth, locality, and seam placement before picking one. Use on "before committing to an interface", "design this API/module/class boundary", "how should this be structured", "compare interface designs", "is this the right abstraction", "design it twice", reviewing a proposed interface shape in a PR — or self-trigger whenever about to write a new interface meeting that bar.

Walk the ordered continue, clear, handoff, delegate, compact decision tree at a phase boundary, and keep any handoff artifact pointer-only — settled specs, plans, ADRs, issues, commits, and diffs referenced by path or URL, never copied inline. Use this when the context window is getting full, you're wondering whether to clear or compact, you need to hand off to another harness, directory, or colleague, you've hit a phase boundary and aren't sure whether to keep going or start fresh, or you want to cache hard-won research before it's lost.

Keep a scannable developer journal that writes itself: discover a day's work from local Claude Code sessions, git commits, and prompt history; interview the user about what mattered and why; and record a tight, dated entry. Ships /dev-diary (write today) and /dev-diary-review (revise a past day). The journal is a separate private repo; this plugin is just the tool.

Diagnose a bug by writing ranked, falsifiable hypotheses before any code change, tagging temporary debug instrumentation for a zero-tolerance sweep, and gating the regression test to a red-then-green proof at the confirmed seam. Use when fixing a bug, debugging a failure, triaging an error, or the user asks to diagnose/root-cause/troubleshoot an issue.

Audits CLAUDE.md/AGENTS.md/SKILL.md instruction files against current repo state, catches claims that have gone stale (a renamed path, a dropped command, a policy that changed) before they get trusted or acted on, and resolves contradictions between layered instruction files (root vs nested, SKILL.md vs its parent AGENTS.md) down to one explicit kept version instead of leaving both to stand. Use before trusting or propagating any instruction-file claim you haven't personally re-checked, whenever onboarding a repo's docs for the first time, right after a refactor/rename/policy change that could invalidate what's documented, or whenever two instruction files (or an instruction file and the actual repo) say different things about the same fact. Trigger phrases: 'audit the docs', 'is AGENTS.md still accurate', 'clean up CLAUDE.md', 'these instructions contradict each other', 'refactor the AGENTS.md files'.

Deploy daily GitHub automation that curates a living, self-invalidating operating index (a 'fleet playbook') for a glob of repos — always pointing at the repos as the source of truth, never posing as it.

Archive old GitHub repositories into a single private graveyard repo as restorable git bundles, then safely delete the originals. Captures full history (branches, tags, PR refs) and never deletes an original until its backup is verified.

Interview the user about a plan before work starts, single-session and no subagents required, walking its design tree and scaling question depth to each branch's stakes (reversibility x blast radius) while offering a recommendation at almost every step. Use on phrases like grill me, interview me about this plan, stress-test this plan, or before starting a nontrivial multi-step change whose design isn't yet settled.

Two reusable multi-agent orchestration templates for research-and-verify work on Claude Code's Workflow tool: fan out research over dimensions, then adversarially verify the claims that research surfaces so plausible-but-wrong findings don't survive. Ships a shared skill, two workflow-script templates (derived-verify, pipelined-verdict-wins), and a worked example.

Scaffold a new marketplace plugin skeleton in one command: a deterministic generator emits a valid plugin.json, an invariant-first SKILL.md, cross-harness AGENTS.md symlinks, a command stub, and a red-by-default eval that fails closed until you implement real checks — then wires it into the marketplace lockfile.

Classify a candidate action as PATCH/MINOR/MAJOR (semver-style blast-radius test) before acting — act silently on PATCH, flag-and-stage MINOR, stop for explicit human sign-off on MAJOR. Use whenever you're mid-task and unsure how much autonomy to take on the next action: which of several implementation paths to pick, whether to overwrite unreviewed state, whether to disable a safety toggle, or any judgment call settings.json's autoMode patterns don't enumerate.

Set up and troubleshoot secretless GitHub Actions -> Tailscale auth via Workload Identity Federation (WIF): GitHub OIDC exchanged for short-lived Tailscale tokens, with no stored API keys or OAuth secrets.

Ship the thinnest end-to-end slice through a system first, then widen it in place — for both software delivery and open-ended investigation/research. Use when scoping new work, de-risking unknowns, or planning how to explore an unfamiliar problem before committing to a full build.

Never assert a fact, completion, or reproduction claim without naming and running the specific check that would prove it false, first.

Route every response element to exactly one voice: prose to human-voice (verdict-first, confidence-tagged), machine-read artifacts to machine-voice (compressed traces, logs, status lines); plus second-opinion, an offer-only subagent validation pipeline that never runs unbidden.

Chart a multi-session effort as a labeled map of typed decision tickets (grilling / prototype / research / task) with explicit dependencies and an open frontier agents self-assign into. Plans; never executes.