Indexion Identity

This runs `indexion identity audit` to flag functions, files, and folders whose names have drifted from what they actually do now. You get a report with expected versus actual summaries, plus recommendations like rename, move, or split. The tool treats each row as a review candidate, not proof, so you verify with `indexion doc graph` or grep before touching anything. It's designed for codebases where names went stale as responsibilities shifted. The audit surfaces work but won't tell you what the correct name should be. You still need to read the code and decide if a file is genuinely unfocused or just thin on declarations.

skills.sh installs: 4.9K
GitHub stars: 2
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add trkbt10/indexion-skills --skill indexion-identity --agent claude-code

Installs into .claude/skills of the current project.

Files

Identity Audit Workflow

Use this skill when checking whether function, file, or folder names still match their contents.

The CLI scans files, folders, and graph-level declaration symbols. It does not treat every local variable, parameter, or field as an independent naming target; those can still influence the containing file summary. File names are evaluated with parent scope, and declaration-heavy files should normally be read as evidence-thin until follow-up inspection proves an actual rename or split.

Pipeline

Run the mechanical scan:

indexion identity audit .

For a machine-readable queue:

indexion identity audit --format=json --output=.indexion/cache/identity/report.json .

Treat each row as a review candidate, not proof. Compare:
- name: the scoped name inferred by the identity package
- expected_summary: what the path/name/scope predicts
- actual_summary: graph-derived declarations, docs, module notes, and path terms
- assessment: whether this is actual drift, overbroad content, or insufficient content
- recommendation: first operation to verify
Verify before editing: