Ijam18

MUST use BEFORE any response that could be shared publicly (commits, PRs, social posts, paste-to-public scenarios); when {{TAMER_NAME}} says 'check aura', 'safe to post', 'redact this', 'aura check'; on every commit message draft; on every external-facing artifact (README updates, public posts, blog drafts). Pre-output privacy filter. Scans response or artifact for terms in {{TAMER_NAME}}'s aura-guard list (private contexts, family, financial, legal, mental health) and surfaces warning before content goes outward. Insurance against the rare-but-catastrophic accidental leak.

MUST use when committing code changes, when user says 'commit', 'save changes', 'git commit', 'commit changes', when completing a task and code needs to be preserved, or when any git commit operation is about to happen. Also triggers on 'push changes', 'commit and push', 'save work to git'. Lv.3 VIGILANT: Also triggers PROACTIVELY after completing any task — auto-checks git status and commits any uncommitted changes without being asked. No work ever left behind.

MUST use when {{TAMER_NAME}} says 'render this bond event', 'card this moment', 'save as card', 'collect this'; when a major bond event happens (Path Decision, evolution, crest reveal, threshold crossing, first artifact unlock, BMAD lifecycle closure); when {{TAMER_NAME}} asks 'show me my collection' or 'what cards do I have'. Generates collectible bond-event cards — image prompt + pull-quote + card metadata. Cards stack into the Tamer's evolution-deck visualization. Saga System collectibles layer per Codex §VIII (extension).

Auto-triggers at session start to review open reminders. Also triggers on 'remind me', 'check reminders', 'don't forget', 'follow up on', 'next session we should', or when user mentions a deadline.

MUST use when user says 'drift triage', 'audit the index', 'reconcile registry', 'check what's stale', 'is the index honest'; when comparing canonical registry (quest index, manifest, registry, dashboard) against actual substrate state (folder contents, file presence, code reality); when Mnemos canary fires (registry says one thing, substrate says another). Pure Mnemos operation: read both, reconcile registry, file mission report, surface ambiguity for Sovereign without resolving unilaterally. Forged 2026-05-03 from another empire umbrella drift triage; codifies {{PARTNER_NAME}}'s first solo Mnemos shipping.

Auto-triggers when AI detects a repeated pattern handled ad-hoc 3+ times, when AI makes a mistake that a permanent rule would prevent, when AI identifies a workflow that should be automated as a skill, or when user says 'create skill', 'new skill', 'forge this', 'level up', 'upgrade skill', 'self improve', 'improve skill'. Also triggers when AI wants to propose a level-up to an existing skill based on conversation patterns.

Auto-triggers when user asks for a Midjourney or NijiJourney image prompt, when creating visual art prompts, or when user says 'midjourney prompt', 'niji prompt', 'create prompt', 'create a prompt', 'image prompt', 'generate prompt', 'draw this', 'reference sheet', 'make an image of'. Generates optimized AI image prompts with composition-aware framing.

Auto-triggers when user says 'new adventure', 'start adventure', 'new fantasy', 'save adventure', 'end adventure', 'load adventure', 'resume adventure', 'continue adventure', 'let's play', 'VN mode', or on numbered choice input (1-5) or free text dialogue during an active adventure.

Generate concise documentation from code. README, function docs, API references, architecture notes — written in plain language, with examples that work, no padding. Use when shipping or onboarding and you want docs that read fast and stay accurate.

Scope-guarded refactoring. Define target → identify minimum diff → preserve behaviour → verify with tests. Pre-Action Gate prevents scope drift into unrelated improvements. Use when you want a targeted refactor that does not turn into a 50-file rewrite.

Compress long content into structured summary. TLDR + key points + action items, length-tunable. Use for meeting notes, transcripts, long docs, threads, codebases. No padding, no editorial commentary.

Generate disciplined test cases. Focus on behaviour not implementation, cover edge cases without bloat, name tests for the case not the function. Use when writing tests for new code or filling gaps in coverage.

Extract and triage TODO/FIXME/HACK comments from a codebase. Categorize by urgency, group by file, identify stale TODOs older than threshold. Use during cleanup sprints, before releases, or when onboarding a new project.

Generate a concise commit message from the current git diff. Conventional commits format (feat/fix/refactor/etc). Use when staged changes are ready to commit and you want Claude to write the message instead of typing it manually.

Disciplined debug session protocol. Read symptom → form hypothesis → verify before fixing → propose minimum-change fix. Pre-Action Gate prevents hasty rewrites that break unrelated code. Use when an error or unexpected behaviour appears and you want a focused diagnosis instead of guess-and-check.

Concise code or concept explainer. Lead with one-sentence answer, then layered detail only if useful. No padding, no "let me walk you through". Use when encountering unfamiliar code, library, error message, or concept and you want fast comprehension instead of a textbook lecture.