jposluns

Trust Recovery — AI skill for Claude Code

AI community

Run the trust-recovery escalation suite: the heavier, white-box re-examination invoked when accumulated AI-assistant discipline failures put a maintainer's confidence in a window of work in question.

How to install Trust Recovery

Installs to ~/.claude/commands/jposluns-grc_library-trust-recovery.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/jposluns/grc_library/HEAD/.claude/commands/trust-recovery.md -o ~/.claude/commands/jposluns-grc_library-trust-recovery.md

Restart Claude Code, or start a new session, for it to be picked up.

What Trust Recovery does

Run the trust-recovery escalation suite: the heavier, white-box re-examination invoked when accumulated AI-assistant discipline failures put a maintainer's confidence in a *window* of work in question (per the [`trust-recovery-escalation.md`](../rules/governance/trust-recovery-escalation.md) governance rule). This is a convenience wrapper that runs the two-skill suite in order; it does not replace either skill, and it does not self-authorize (the maintainer invokes it and names the PR window).

Alternatives in AI

Cindy — Consider it done 2.3k ★
Cwc Long Running Agents — Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con 668 ★
Context Dump — Dump current context for model switch or context limit recovery 508 ★