Skill Claude CodeCodex
Read this skill when you want to understand your affect reading, interpret what it means for your current work, or decide how to respond to elevated pressure. Covers the traditions that ground the instrument, what each dimension measures, the choices available to you, and what the instrument cannot see.
Skill Claude CodeCodex
The MVP commitment tracker. After each cycle a scanner writes commitment-shaped statements to a captures log. This skill explains what to do when the sensorium shows pending captures.
Skill Claude CodeCodex
Patterns for code execution in the Podman sandbox. Covers runcode, serve mode, workspace management, and common failure modes.
Skill Claude CodeCodex
How the Coder agent drives an OpenCode session via dispatchcoder — the engineering loop, when to dispatch, and how to verify the result is real (vs. claimed).
Skill Claude CodeCodex
Decision framework for when and how to delegate work to specialist agents and agent teams. Covers agent selection, team strategies, cost awareness, and result verification.
Skill Claude CodeCodex
How to answer an askdeputy call concisely. Only meaningful in Phase 2+ (long-lived deputies).
Skill Claude CodeCodex
How a deputy should structure its briefing XML — what to include, what to leave out, how to weight relevance.
Skill Claude CodeCodex
When a deputy should emit a sensory event (Tier 1) vs request a wakeup (Tier 2), and when to do neither. Only meaningful in Phase 3+.
Skill Claude CodeCodex
When and how to use the document library.
Skill Claude CodeCodex
How to handle inbound emails — decide whether to reply, compose the response, and send it back via the comms agent.
Skill Claude CodeCodex
When and how to use the memory stores, and which memory specialist (cognitive / Observer / Remembrancer) to delegate to.
Skill Claude CodeCodex
How to use the Strategy Registry, Learning Goals, affect-performance signals, the Study-Cycle pipeline, and the Metacognitive Scheduler — the substrate for directing your own development.
Skill Claude CodeCodex
How to orchestrate work across large documents and multi-agent delegations without burning token budgets. Reconnaissance-first, search-then-read, parallel-after-reconnaissance.
Skill Claude CodeCodex
Maintain a personal index of interesting things, open questions, and follow-ups across sessions.
Skill Claude CodeCodex
How to introspect and control the forecaster, manage endeavour lifecycle, adjust feature weights, edit tasks, view forecast breakdowns, and handle failures.
Skill Claude CodeCodex
How to decompose complex goals into structured plans with steps, dependencies, and risk identification.
Skill Claude CodeCodex
Seven-step health check procedure using existing introspection tools. Run on boot, daily, or when meta-states indicate anomalies.
Skill Claude CodeCodex
Run shell commands in a sandboxed Docker container with the project directory mounted at /workspace.
Skill Claude CodeCodex
Index to the territory. Subsystem inventory, the agent graph, cross-subsystem interactions, and invariants. Read this when something unfamiliar shows up.
Skill Claude CodeCodex
How pre-mortems and post-mortems work, what verdicts mean, and how to act on appraisal results.
Skill Claude CodeCodex
Search and extraction strategy. Teaches the researcher which of the 8 web tools to use at each stage of a research cycle.
Skill Claude CodeCodex
Decision criteria for delegating to the writer agent vs synthesising directly in your own response.
Skill Claude CodeCodex
When and how to render a promoted export to PDF via the exportpdf tool. Reads the writer's draft → export → PDF lifecycle and the operator-facing failure modes when the host is missing pandoc or tectonic.
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: