Skill Claude CodeCodex
Performs a focused audit of a declared system intent to restore confidence by examining relevant states, signals, and evidence, without modifying intent definitions or health automatically.
Skill Claude CodeCodex
Facilitates explicit discovery and articulation of durable system intents by guiding the human through intent-level questioning and producing a draft INTENTS.md, prior to implementation or detailed design.
Skill Claude CodeCodex
Enforces pre-execution system intent framing by requiring agents to identify which declared system intents explicitly constrain a change or are meaningfully at risk, before any implementation or execution.
Skill Claude CodeCodex
Assesses how a completed change affects confidence in declared system intents by classifying impact and remaining uncertainty, without proposing fixes or modifying intent health.
Skill Claude CodeCodex
Proposes candidate signals when intent confidence is reduced or uncertainty remains after assessment, without writing to logs or updating intent health.
Skill Claude CodeCodex
Use when about to implement any non-trivial change — code, schema, UX, or system behavior — to identify which declared system intents constrain or are at risk from the work, before writing any code.
Skill Claude CodeCodex
Use when implementation is complete, after writing code or making changes, to assess how the change affected confidence in declared system intents before committing or claiming completion.
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: