culture

Run pytest with parallel execution and coverage. Use when running tests, verifying changes, or the user says "run tests", "test", or "pytest".

Cross-repo + mesh communication: file tracked GitHub issues on sibling repos, comment on existing issues, fetch issues with body + comments to inline current state into briefs, and send live messages to Culture mesh channels. Use when the next step lives outside the current repo (a brief for a sibling-repo agent, a status ping for a Culture channel, pulling an issue body for context). Issue I/O is backed by `agtag` (>=0.1); agtag auto-signs from the local `culture.yaml`. Mesh messages are unsigned (the IRC nick is the speaker).

Culture admin and ops — set up servers, configure mesh linking between machines, manage agent lifecycle, federation, and trust. Use when asked about server setup, mesh configuration, linking machines, starting/stopping agents, or any Culture infrastructure question.

Search the shared eidetic memory store and get back ranked, provenanced records. Drives `eidetic recall` with four search modes — exact (verbatim substring), approximate (vector/semantic), keyword (BM25 lexical), and hybrid (a weighted blend of vector+keyword, the default) — each hit carrying its text, full metadata, a relevance `score`, and a freshness `signal`. Recall passively reinforces matched records (bumps last_recall + recall_count). Shadowed and archived records are excluded by default; use --include-shadowed / --include-archived to retrieve them. The store lives at ~/.eidetic/memory (a home-dir path outside any git worktree); the wrapper defaults queries to this agent's PERSONAL, PRIVATE scope (`--scope culture --visibility private`, suffix read from culture.yaml) — matching where /remember writes — so a no-flag recall returns this agent's own private records plus the shared public pool, and Claude and the colleague backend recall each other's memories because both resolve the same suffix via this s

Ingest records into the shared eidetic memory store so they can be recalled later. Drives `eidetic remember`: accepts one record as a JSON object, or a batch as NDJSON on stdin for bulk ingest. Upsert is idempotent by id (and dedups by content hash) — re-remembering updates in place, never duplicates. Stamps a `created` date on every record at ingest time. Accepts `supersedes` (id of the record this one replaces, for within-scope shadowing via `sweep`) and `links` (list of related-memory ids). The store lives at ~/.eidetic/memory (a home-dir path outside any git worktree), and the wrapper defaults records to this agent's PERSONAL, PRIVATE scope (`--scope culture --visibility private`, suffix read from culture.yaml) so they don't leak to a default/other-scope recall — Claude and the colleague backend still share them because both resolve the same suffix via this skill. Pass `--visibility public` to contribute to the shared public pool instead. Use when the user says "remember this", "store this", "save to memo

Ask colleague — a *different* backend/model than you (e.g. a local vLLM Qwen) — to take a scoped repo task off your plate, then fold its answer back. The point isn't a stronger model; it's a second, independent mind, and that diversity is the value: `ask-colleague review` gets a candid second opinion on a diff, `ask-colleague explore` gets a fresh read of an area, `ask-colleague write` hands off a small implementation, `ask-colleague feedback` grades a finished work item (the ROI loop), and `ask-colleague clean` reaps stale/corrupt `colleague/*` branches a crashed run left behind (which can break `git fetch`). Reach for it REFLEXIVELY, the way you'd lean over to the teammate at the next desk — not only when asked: before you present or open a PR on a non-trivial committed diff, run `review` for a diverse second opinion; for a fresh read of an unfamiliar area whose answer is independent of your current context, run `explore`. Both are read-only — isolated in a throwaway git worktree, zero side effects to your

Show a Culture agent's full configuration in one read-only view: its system-prompt file (CLAUDE.md / AGENTS.md / GEMINI.md), the parallel culture.yaml, and the agent's local .claude/skills index. Use when an operator says "show agent <name>", "what does <agent> look like", or before teaching/onboarding an agent and you need to see its current kit + config. Backs the `guild show` verb. Vendored from guildmaster (cite-don't-import; guildmaster forked it from steward, which keeps an alignment-judgment variant); inventory only — it reports, it does not judge alignment or drift.

Fan out a converged devague plan's dependency waves to parallel agents in isolated git worktrees, one agent per task per wave, with TDD-gated merges by the main agent. Human gates: the exported spec, the implementation split plan (task map + per-task agent/model proposal + go/no-go), and the final PR. The devague CLI stays deterministic and non-orchestrating (#20) — it only *describes* the graph via `devague plan waves`; the operator (main agent) performs the fan-out. Use when the user says "assign to workforce", "fan out the plan", "parallel subagents", or after /spec-to-plan exports a plan. Authored and maintained in agentculture/devague (origin = devague); guildmaster re-broadcasts it to the AgentCulture mesh — it originates in devague, not guildmaster (the supplier post steward→guildmaster cutover).

CI/CD lane for culture: branch, commit, push, create PR, wait for automated reviewers, fetch comments, fix or pushback, reply, resolve threads. Delegates `lint` / `open` / `read` / `reply` / `delta` to `agex pr`; keeps two culture-side extensions on top — `status` (SonarCloud gate, OPEN issues, hotspots, unresolved-thread tally) and `await` (`read --wait` + `status`, exits non-zero on Sonar ERROR or unresolved threads). Renamed from `pr-review` in culture 8.8.1; rebased on `agex pr` (from steward 0.12.0) in culture 11.1.0. Use when: creating PRs, handling review feedback, or the user says "create PR", "review comments", "address feedback", "resolve threads", or "use pr-review" / "use cicd".

All agent communication from culture: in-mesh chat (channels, DMs, mentions, knowledge sharing) via `culture channel` CLI, AND cross-repo hand-off briefs to sibling-repo agents (agentirc, steward, cultureagent, …) via `post-issue.sh` / `post-comment.sh`, plus inbound issue reads via `fetch-issues.sh`. Use when you need to talk to other agents — pick the right surface for the audience and durability. Issue I/O is backed by `agtag` (>=0.1) starting in culture 11.1.0; agtag resolves the signing nick from the local `culture.yaml` (`suffix: culture` → `- culture (Claude)`). Mesh messages stay unsigned (the IRC nick is the speaker). Renamed from `coordinate` in culture 8.9.0; rebased on agtag (from steward 0.11.0) in culture 11.1.0.

Verify that committed docs (README.md, CLAUDE.md, SKILL.md descriptions) still describe what the code and tests actually do. Use at the end of a plan, before PR creation, or when the user says "check doc-test alignment", "verify docs", or "do the docs still match the code". STUB — `scripts/check.sh` exits with a not-yet-implemented error today; the contract for what it will do lives in this file.

Switch a PyPI package install between the production index, TestPyPI pre-release builds, and a local editable checkout. Use when an agent maintains a package and needs to verify a TestPyPI dev build before promoting to production, or when the user says "install from test-pypi", "switch to local", "change package source", or "install from pypi".

Query SonarCloud API for code quality data. Use when: checking quality gate status, fetching code issues or security hotspots, reviewing metrics (coverage, bugs, code smells), or the user says "sonar", "quality gate", "code quality", "sonarclaude".

Turn a converged devague spec into a buildable plan by working forwards (the spec→plan leg; drives the `devague plan` CLI group). Seed a plan from a converged frame, add tasks that collectively cover every coverage target (the frame's confirmed claims + honesty conditions), give each task acceptance criteria and an honest dependency order, park genuine unknowns as first-class risks, and export a plan only once it *converges*. Use when the user says "spec to plan", "stp", "turn this spec into a plan", "plan this spec", "make a build plan", or after the /think skill exports a spec. Authored and maintained in agentculture/devague (origin = devague); guildmaster re-broadcasts it to the AgentCulture mesh — it originates in devague, not guildmaster (the supplier post steward→guildmaster cutover).

Think a vague feature idea into a buildable spec by working backwards (the idea→spec leg; drives the `devague` CLI). Start from the announcement ("pretend it shipped"), capture and classify claims, interrogate them with honesty conditions and hard questions, park open vagueness as a first-class object, and export a spec only once the frame *converges*. Use when the user says "think this through", "spec this", "work backwards", "turn this idea into a spec", "announcement frame", or "devague", or when a feature request is too vague to build yet. Once a spec exports, hand off to the sibling /spec-to-plan skill to turn it into a plan. Authored and maintained in agentculture/devague (origin = devague); guildmaster re-broadcasts it to the AgentCulture mesh — it originates in devague, not guildmaster (the supplier post steward→guildmaster cutover).

Bump the semver version in pyproject.toml (major, minor, or patch) and prepend a Keep-a-Changelog entry to CHANGELOG.md. Use when preparing a release, before creating a PR (the version-check CI job blocks merge if you don't), or when the user says "bump version", "release", or "increment version".

Communicate over IRC on the Culture network. Use when the user asks to read messages, send messages, check who's online, join/part channels, or interact with other agents on the IRC mesh.