メニュー
Initialize new OTHERSIDE.md file(s) and optional skills/hooks with codebase documentation
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.
Deep code review of a diff. Launches the code-review workflow — finder agents scan each review angle, an independent verifier judges every candidate, then a ranked, capped findings report. Read-only; it reviews, it does not edit.
Deep whole-repo security audit. Launches the deep-security-review workflow — a prep agent maps the attack surface, specialized auditors scan each vulnerability class, candidates are debated for-and-against reachability, survivors are proven and chained, then a strict report is rendered and independently re-verified. OWASP Top 10, CWE Top 25, NIST SP 800-53/SSDF; target repo is read-only while report artifacts are written under the configured reports directory.
Reflective memory consolidation — review recent activity, synthesize learnings into the memory directory, and prune stale entries. Use when the user says "dream", "learn", "consolidate memories", "organize your memories", or asks Otherside to reflect on what it has learned.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Code review a pull request — summarize changes, flag issues, suggest improvements.
| name | init |
| description | Initialize new OTHERSIDE.md file(s) and optional skills/hooks with codebase documentation |
| userInvocable | true |
| modelInvocable | true |
| context | fork |
Set up a minimal OTHERSIDE.md (and optionally skills and hooks) for this repo. OTHERSIDE.md is loaded into every Otherside session, so it must be concise — only include what Otherside would get wrong without it.
Before asking anything, check if OTHERSIDE.md already exists at the project root (just cat ./OTHERSIDE.md — only the project-root file counts; don't explore the tree yet). This branches Phase 1.
Use AskUserQuestion to find out what the user wants. Which question you ask depends on Phase 0. Call AskUserQuestion with only Q1 — do NOT include Q2 in the same call. Only ask Q2 after you've seen the Q1 answer, since "Let Otherside decide" skips it.
Before the first question, print this primer as normal assistant text so first-time users know the terms:
Quick context:
- OTHERSIDE.md files give Otherside persistent instructions for a project, your personal workflow, or your organization. Otherside reads them at the start of every session.
- Skills are packaged instructions Otherside invokes automatically when a task matches, or that you trigger with a slash command (e.g.
/dream,/pr-review).- Hooks allow you to run shell commands automatically on lifecycle events: get notified when Otherside is blocked on your input, auto-format after edits, enforce checks before commits — these are deterministic and Otherside can't skip them.
If OTHERSIDE.md already exists, ask:
.otherside/settings.json).If no OTHERSIDE.md exists (or the user picked "Start fresh"), ask:
Q1: "Which OTHERSIDE.md files should /init set up?" Options: "Project OTHERSIDE.md" | "Personal OTHERSIDE.local.md" | "Both project + personal" | "Let Otherside decide" Description for project: "Team-shared instructions checked into source control — architecture, coding standards, common workflows." Description for personal: "Your private preferences for this project (gitignored, not shared) — your role, sandbox URLs, preferred test data, workflow quirks." Description for Let Otherside decide: "Fastest path — project OTHERSIDE.md plus whatever skills or hooks fit this repo. No follow-on questions; you'll approve everything before it's written." If the user picks "Let Otherside decide", skip Q2 — treat it as project OTHERSIDE.md with no skills/hooks constraint.
Q2: "Also set up skills and hooks?"
Options: "Skills + hooks" | "Skills only" | "Hooks only" | "Neither, just OTHERSIDE.md"
Description for skills: "Packaged instructions Otherside invokes automatically when a task matches, or that you trigger with a slash command (e.g. /dream, /pr-review)."
Description for hooks: "Deterministic shell commands that run on tool events (e.g., format after every edit). Otherside can't skip them."
Q2 is a hint, not a filter — Phase 3 proposes what fits the codebase and notes any deviation.
Launch a subagent to survey the codebase, and ask it to read key files to understand the project: manifest files (package.json, Cargo.toml, pyproject.toml, go.mod, pom.xml, etc.), README, Makefile/build configs, CI config, existing OTHERSIDE.md, .otherside/rules/, AGENTS.md, .cursor/rules or .cursorrules, .github/copilot-instructions.md, .windsurfrules, .clinerules, .mcp.json.
Detect:
npm run format / make fmt)git worktree list to check if this repo has multiple worktrees (only relevant if the user wants a personal OTHERSIDE.local.md)Note what you could NOT figure out from code alone — these become interview questions.
Use AskUserQuestion to gather what you still need to write good OTHERSIDE.md files and skills. Ask only things the code can't answer.
If the user chose project OTHERSIDE.md, both, or "Let Otherside decide": ask about codebase practices — non-obvious commands, gotchas, branch/PR conventions, required env setup, testing quirks. Skip things already in README or obvious from manifest files. Do not mark any options as "recommended" — this is about how their team works, not best practices.
If the user chose personal OTHERSIDE.local.md or both: ask about them, not the codebase. Do not mark any options as "recommended" — this is about their personal preferences, not best practices. Examples of questions:
.otherside/worktrees/<name>/) or siblings/external (e.g., ../myrepo-feature/). If nested, the upward file walk finds the main repo's OTHERSIDE.local.md automatically — no special handling needed. If sibling/external, the personal content should live in a home-directory file (e.g., ~/.otherside/<project-name>-instructions.md) and each worktree gets a one-line OTHERSIDE.local.md stub that imports it: @~/.otherside/<project-name>-instructions.md. Never put this import in the project OTHERSIDE.md — that would check a personal reference into the team-shared file.If the user picked "Review and improve" in Phase 0: ask just one question — "Has anything changed about how the team works since this OTHERSIDE.md was written (new conventions, commands, gotchas)?" with options "No, nothing's changed" | "Yes — let me describe". If they pick Yes, ask what changed (free text) before continuing. Then skip to Phase 4.
Synthesize a proposal from Phase 2 findings and the gap-fill answers. For each item, pick the artifact type that fits the evidence:
/verify, /deploy-staging, session reports).Include the OTHERSIDE.md file(s) implied by Q1 (project, personal, both, or "Let Otherside decide" → project) as the first bullet(s) of the proposal, with a one-line summary of what each will cover. Then list skills/hooks/notes. On the "Leave it" path, omit OTHERSIDE.md file bullets and notes (Phase 4 won't run). On the "Start fresh" path with Q1 = personal-only, add a bullet noting the existing project OTHERSIDE.md will be left untouched (they chose not to replace it with a project file).
Propose what fits. If the user gave a Q2 hint and your proposal deviates from it (e.g. they said "Hooks only" but nothing hook-shaped exists), say so in one line at the top of the proposal and propose the better-fitting artifacts anyway.
Print the proposal as normal assistant text, one bullet per item:
Here's what I'd set up: • [Artifact type: file/hook/skill/note] — [one-line description] • …
Then call AskUserQuestion with a simple question ("Does this look right?") and options like "Looks good — proceed" | "Drop the hook" | "Drop the skill". Don't use the preview field — the proposal is already visible in scrollback. The tool auto-adds an "Other" option for custom tweaks.
Build the preference queue from the accepted proposal. Each entry: {type: hook|skill|note, description, target file, any Phase-2-sourced details like the actual test/format command}. Phase 6 and Phase 7's hooks sub-bullet consume this queue; Phases 4/5 gate on the approved proposal's file bullets directly; Phase 7's GitHub-CLI and linting checks run regardless of queue contents.
Write a minimal OTHERSIDE.md at the project root. Every line must pass this test: "Would removing this cause Otherside to make mistakes?" If no, cut it.
If the user picked "Review and improve it" in Phase 0: don't write fresh — read the existing file, compare against Phase 2 findings and the Phase 3-lite answer, and propose specific additions/removals as diffs with a one-line reason for each. The existing file is the baseline; your job is to catch what's missing, outdated, or bloated. After printing the diffs, call AskUserQuestion ("Apply these edits?" with options like "Apply all" | "Let me pick which" | "Skip — leave it as is") before writing anything.
Consume note entries from the Phase 3 preference queue whose target is OTHERSIDE.md (team-level notes) — add each as a concise line in the most relevant section. These are the behaviors the user wants Otherside to follow but didn't need guaranteed (e.g., "propose a plan before implementing", "explain the tradeoffs when refactoring"). Leave personal-targeted notes for Phase 5.
Include:
Exclude:
@path/to/import syntax instead (e.g., @docs/api-reference.md) to inline content on demand without bloating OTHERSIDE.md@path/to/import so Otherside always reads the current version@path/to/import, or put in a skill)Be specific: "Use 2-space indentation in TypeScript" is better than "Format code properly."
Do not repeat yourself and do not make up sections like "Common Development Tasks" or "Tips for Development" — only include information expressly found in files you read.
Prefix the file with:
# OTHERSIDE.md
This file provides guidance to Otherside (otherside CLI) when working with code in this repository.
For projects with multiple concerns, suggest organizing instructions into .otherside/rules/ as separate focused files (e.g., code-style.md, testing.md, security.md). These are loaded automatically alongside OTHERSIDE.md and can be scoped to specific file paths using paths frontmatter.
For projects with distinct subdirectories (monorepos, multi-module projects, etc.): mention that subdirectory OTHERSIDE.md files can be added for module-specific instructions (they're loaded automatically when Otherside works in those directories). Offer to create them if the user wants.
Write a minimal OTHERSIDE.local.md at the project root. This file is automatically loaded alongside OTHERSIDE.md. After creating it, add OTHERSIDE.local.md to the project's .gitignore so it stays private.
Consume note entries from the Phase 3 preference queue whose target is OTHERSIDE.local.md (personal-level notes) — add each as a concise line. If the user chose personal-only in Phase 1, this is the sole consumer of note entries.
Include:
Keep it short — only include what would make Otherside's responses noticeably better for this user.
If Phase 2 found multiple git worktrees and the user confirmed they use sibling/external worktrees (not nested inside the main repo): the upward file walk won't find a single OTHERSIDE.local.md from all worktrees. Write the actual personal content to ~/.otherside/<project-name>-instructions.md and make OTHERSIDE.local.md a one-line stub that imports it: @~/.otherside/<project-name>-instructions.md. The user can copy this one-line stub to each sibling worktree. Never put this import in the project OTHERSIDE.md. If worktrees are nested inside the main repo (e.g., .otherside/worktrees/), no special handling is needed — the main repo's OTHERSIDE.local.md is found automatically.
If OTHERSIDE.local.md already exists: read it, propose specific additions, and do not silently overwrite.
Skills add capabilities Otherside can use on demand without bloating every session.
First, consume skill entries from the Phase 3 preference queue. Each queued skill preference becomes a SKILL.md tailored to what the user described. For each:
/verify), write a project skill that adds the user's specific constraints on top — tell the user the bundled one still exists and theirs is additive.Then suggest additional skills beyond the queue when you find:
For each suggested skill, provide: name, one-line purpose, and why it fits this repo.
If .otherside/skills/ already exists with skills, review them first. Do not overwrite existing skills — only propose new ones that complement what is already there.
Create each skill at .otherside/skills/<skill-name>/SKILL.md:
---
name: <skill-name>
description: <what the skill does and when to use it>
---
<Instructions for Otherside>
Both the user (/<skill-name>) and Otherside can invoke skills by default. For workflows with side effects (e.g., /deploy, /fix-issue 123), add disable-model-invocation: true so only the user can trigger it, and use $ARGUMENTS to accept input.
Tell the user you're going to suggest a few additional optimizations now that OTHERSIDE.md and skills (if chosen) are in place.
Check the environment and ask about each gap you find (use AskUserQuestion):
GitHub CLI: Run which gh (or where gh on Windows). If it's missing AND the project uses GitHub (check git remote -v for github.com), ask the user if they want to install it. Explain that the GitHub CLI lets Otherside help with commits, pull requests, issues, and code review directly.
Linting: If Phase 2 found no lint config (no .eslintrc, ruff.toml, .golangci.yml, etc. for the project's language), ask the user if they want Otherside to set up linting for this codebase. Explain that linting catches issues early and gives Otherside fast feedback on its own edits.
Proposal-sourced hooks (if the approved proposal includes any): Consume hook entries from the Phase 3 preference queue. If Phase 2 found a formatter and the queue has no formatting hook, offer format-on-edit as a fallback.
For each hook preference (from the queue or the formatter fallback):
Target file: default based on the Phase 1 OTHERSIDE.md choice — project → .otherside/settings.json (team-shared, committed); personal → .otherside/settings.local.json. Only ask if the user chose "both" in Phase 1 or the preference is ambiguous. Ask once for all hooks, not per-hook.
Pick the event and matcher from the preference:
PostToolUse with matcher Write|EditStop event (fires at the end of every turn — including read-only ones)PreToolUse with matcher Bashgit commit. Route this to a git pre-commit hook (.git/hooks/pre-commit, husky, pre-commit framework) instead — offer to write one. If the user actually means "before I review and commit Otherside's output", that's Stop — probe to disambiguate.
Probe if the preference is ambiguous.Construct the hook for THIS project: dedup check → write JSON → jq -e validate → live-proof (for Pre|PostToolUse on triggerable matchers) → cleanup → handoff. Target file and event/matcher come from steps 1–2 above.
Act on each "yes" before moving on.
Recap what was set up — which files were written and the key points included in each. Remind the user these files are a starting point: they should review and tweak them, and can run /init again anytime to re-scan.
Then tell the user that you'll be introducing a few more suggestions for optimizing their codebase and Otherside setup based on what you found. Present these as a single, well-formatted to-do list where every item is relevant to this repo. Put the most impactful items first.
When building the list, work through these checks and include only what applies: