agentleFS
eisbaweisbaw/mped-skills/skills/aula-pii-scan/SKILL.md

aula-pii-scan

Skill11 starsChanged 3 months agoMITView on GitHub

Pre-push PII scanner for the Aula project. Scans tracked workspace files and full git history for known PII terms (real profile IDs, institution codes, names, addresses, contact info). Must pass before pushing.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use git filter-repo --replace-text to scrub history if PII was ever committed

    line 46
  2. Very specific:

    After history rewrite: git reflog expire --expire=now --all && git gc --aggressive --prune=now

    line 47
  3. Very specific:

    If new PII is discovered during development (new profile IDs, names, addresses, etc.), add them to pii-terms.txt (one per line, # for …

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Aula PII Scan -- Pre-Push PII Scanner

Scans the workspace (tracked files) and full git history for known Aula PII terms that must never reach a public remote. Run this before every push.

PII terms live in pii-terms.txt alongside this skill. That file is .gitignored on purpose: the list of terms IS the PII, so it must never be committed. Only the redacted pii-terms.txt.example template is tracked.

On a fresh checkout, create the real list once:

SKILL_DIR="$HOME/.claude/skills/aula-pii-scan"
cp "$SKILL_DIR/pii-terms.txt.example" "$SKILL_DIR/pii-terms.txt"
# then edit pii-terms.txt and replace the placeholders with real terms

Procedure

Step 1: Run the scan script

SKILL_DIR="$HOME/.claude/skills/aula-pii-scan"
bash "$SKILL_DIR/scan.sh"

This scans:

  1. Workspace -- all git-tracked files (excluding secrets/) for any PII term
  2. Git history -- git log -p --all -S <term> for each term across all commits
  3. Sensitive files -- checks if .har, .pcap, or secrets/* files were ever committed

Step 2: Report the result

The script exits 0 (PASS) or 1 (FAIL).

If PASS: Report "Aula PII scan passed. Safe to push."

If FAIL: Report each finding with file, line, and matched term. The push must be blocked until all findings are resolved. Typical fixes:

  • Move real IDs to secrets/ (gitignored) and use synthetic values in code
  • Use git filter-repo --replace-text to scrub history if PII was ever committed
  • After history rewrite: git reflog expire --expire=now --all && git gc --aggressive --prune=now

Step 3: Adding new PII terms

If new PII is discovered during development (new profile IDs, names, addresses, etc.), add them to pii-terms.txt (one per line, # for comments) so future scans catch them. Never add real terms to pii-terms.txt.example -- keep that file redacted.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.