Retrospective review of your existing Claude Code history — which sessions wrote outside the project they were working in. Local and read-only; no prompt content is inspected.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add crescerelabs/sentience-governor --skill sentience-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sentience Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crescerelabs-sentience-review)More formats (shields.io, HTML) on the badges page.
---
name: sentience-review
description: |
Retrospective review of your existing Claude Code history —
which sessions wrote outside the project they were working in.
Local and read-only; no prompt content is inspected.
disable-model-invocation: true
allowed-tools: Bash(sentience scan *)
---
!`sentience scan`
Render the command output above verbatim in a code block. Do not
summarize, reinterpret, reformat, rank, re-count, read transcript
files, or compute substitute results. Do not add findings, severity,
risk or confidence language of any kind — the review deliberately
carries no scores. If the review reports that no sessions stand out,
show it as-is and stop; that is a result, not a failure. Do not use
Sentience report headings unless they appear in the command output.
Add no prose of your own after the code block. If the user explicitly
asks you to explain it, reply starting with
`Interpretation (not Sentience output):` and use only the rendered
report.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...