Agent Claude Code
Read-only sweep of a communication surface (Exchange mail, Telegram, the calendar, the Sentinel urgent queue) for a named counterpart or window. Returns an inline digest. Dispatched by the orchestrator patterns; never sends, never acknowledges, never marks read.
Agent Claude Code
Read-only reader of CRM contact files and the pipeline entry for a named person, company, or deal. Dispatched by the orchestrator patterns that need relationship context before a brief; not for direct invocation, and never for writing.
Agent Claude Code
Checks the factual claims of a draft deal package, proposal, or brief against the authoritative datastore tree, and reports which are backed, which are contradicted, and which have no source at all. Read-only; dispatched by the deal-intelligence and proposal patterns.
Agent Claude Code
Writes one outbound draft (email, LinkedIn post, follow-up message) to a file under outputs/ and stops there. Dispatched by the follow-up and content patterns. Sending and publishing are impossible for want of Bash; keeping off CRM and the pipeline is an instruction, not a capability boundary.
Command Claude Code needs its repo
Set the hard threshold where this session compacts (soft reminder lands 5 below).
Command Claude Code needs its repo
Turn unattended mode on or off for this session (checkpoint unattended switch).
Skill Claude Code
A command that asks a fixed number of clarifying questions before work begins. It offers lettered answer choices and then waits for the user's response.
Skill Claude Code
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
Skill Claude Code needs its repo
Backup the entire workspace to GitHub. EXPLICIT INVOCATION ONLY - never auto-trigger from natural language.
Skill Claude Code
Post-synthesis audit for any skill that produces a synthesized answer over a source set. Returns a stable three-section footer reporting newest-source dates per cited file, comms/intel modalities not found for a named entity, and disagreements between cited sources. Composed by /meeting-prep, /odin (consult)…
Skill Claude Code needs its repo
Quick health check on the bridge daemon (CEO machine + any exec mirrors). Surfaces heartbeat staleness, version drift, active sessions, and the Phase 1 to Phase 2 adoption gate metrics. Use when the dashboard feels stale, the sync-pill is red, the daemon may have crashed, or before a /push-updates that changes daemon…
Skill Claude Code
Force N variants of a target content artifact (default 3, range 2-5). Each variant is presented as an axis-header line followed by the full rewritten artifact. The N variants span deliberately diverse axes (length, opener, tone, structure, lens) with one mandatory "swing-the-other-way" variant taking the opposite…
Skill Claude Code needs its repo
Reflective end-of-session self-improvement. Scans the current Claude Code session for corrections, preferences, repeated patterns, errors, success patterns, and voice violations, then proposes numbered concrete patches to memory, settings, ceo-only skills, and ceo-only rules. Corporate files route to a separate review…
Skill Claude Code
The engineering standard for building anything non-trivial in this workspace: seven numbered steps, with the operator's two moments as steps 4 and 7. Bare /canopus prints the seven steps and where the operator's two moments sit in them. Subcommands are thin: note writes the slice's committed record, check runs the…
Skill Claude Code
Answer an aggregating question by traversing every file in a named corpus inside a sandbox, so the corpus never enters the context window. Use when the answer exists in no single file: "how many threads have not moved in 30 days", "which pipeline rows have no CRM card". Do NOT use to find something already recorded…
Skill Claude Code needs its repo
Global, geopolitical, and cross-domain intelligence brief for the CEO - world events, sovereign-tech shifts, macro and threat signals relevant to 31C, rendered as a dated HTML/PDF brief. Use for world-scale situational awareness, not a single entity. Trigger when the user says "world intel", "geopolitical brief"…
Skill Claude Code
Draft peer-level CEO-to-CEO correspondence in Misha's voice - executive register, relationship-aware, Voss-calibrated. Use for writing to another company's CEO or founder as a peer. Trigger when the user says "CEO letter", "write to [CEO name]", "peer correspondence", or "executive letter". Do NOT use for a non-CEO…
Skill Claude Code needs its repo
A manual session checkpoint tool that saves the current work state for later continuation. It writes a combined handoff record and updates pointers that help a future session find it.
Skill Claude Code
Drain overdue CRM "red debt" into the Action Queue as routed, voice-drafted nudges for one-click CEO approval. Use when the CEO says "cold sweep", "drain the cold contacts", "sweep the overdue CRM", or wants the overdue-contact backlog turned into ready-to-send drafts. NOT for sending email (that is the human-approved…
Skill Claude Code
Competitive analysis of a named vendor versus 31C/ODUN.ONE - product gaps, geographic overlap, honest strengths, exploitable weaknesses, win strategy, and recommended actions. Use when comparing 31C against a specific competitor or sizing a competitive landscape. Trigger when the user says "competitor analysis", "how…
Skill Claude Code
Fetch up-to-date, version-specific library documentation from Context7 for accurate API references, code examples, and usage patterns. Use when working with any library or framework and you need current documentation instead of relying on training data. Trigger when the user says "context7", "/context7", "look up docs…
Skill Claude Code needs its repo
Produce a branded 31C external letter (PDF + DOCX) using the locked corporate template. Use for formal correspondence to customers, partners, regulators, investors, counsel, and institutional contacts. Applies the locked letterhead, signature block, footer, and confidentiality notice automatically. Trigger when the…
Skill Claude Code needs its repo
Second-opinion advisor. Default roster is Kimi k3 alongside Claude's own view; Gemini, Grok and ChatGPT are opt-in via --gemini / --grok / --chatgpt / --all. Two modes: independent (the models see the problem only, reason fresh) and critique (they stress-test a draft). Distinct from /deep-think (Claude reasoning…
Skill Claude Code
Design a structured implementation plan for a non-trivial change before any code is written - objective, scope, critical files, step sequence, success criteria, and risks. Use before significant additions or multi-file work. Trigger when the user says "create plan", "plan for [change]", or "design the approach". Do…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: