lean-privacy
Skill2 starsChanged 56 days agoMITView on GitHub
Runs token-efficient defensive privacy and PII reviews for Cursor and Codex. Finds likely emails, phones, and identifier fields in local code and logs without printing the values, then reports compact minimization and redaction fixes. Use when the user asks for privacy review, PII, GDPR, logging of personal data, data minimization, or redaction. Do not use for collecting PII on people, doxxing, or building marketing lists.
In this repository21 other files it gives its agents.
- lean-cryptoSkill
- lean-mobileSkill
- lean-secSkill
- lean-webSkill
- lean-a11ySkill
- lean-depsSkill
- lean-docsSkill
- lean-perfSkill
- lean-reviewSkill
- lean-ciSkill
- lean-cloudSkill
- lean-costSkill
- lean-hardeningSkill
- lean-iotSkill
- lean-netSkill
- lean-dfirSkill
- lean-ir-playbookSkill
- lean-malwareSkill
- lean-osintSkill
- lean-phishSkill
- lean-threat-modelSkill
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
- Very specific: line 38
Run pii. Treat hits as locations, not a contact list.
- Very specific: line 44
Never echo a live email, phone, national id, or card number.
- Distinctive: line 45
Do not build dossiers or export a PII CSV.
≈ “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.
Files
Lean Privacy
Defensive PII hygiene in this workspace. Scripts report kinds and locations only. Never print the values.
Let SKILL_ROOT be the folder that contains this SKILL.md. Prefer python3; on Windows use py -3.
python3 "$SKILL_ROOT/scripts/lean_privacy.py" pii .
python3 "$SKILL_ROOT/scripts/lean_privacy.py" trim --chars 2500 path/to/out.txtMode
Default lean.
| Mode | Budget |
lean | pii + up to 8 slices; references/minimize.md; ≤6 findings |
standard | + references/logs.md; up to 16 slices; ≤10 findings |
deep | needed refs only; ≤16 findings |
Workflow
- Run
pii. Treat hits as locations, not a contact list. - Confirm logging, analytics, and error dumps that include user fields.
- Recommend delete/redact/minimize. Patch only if asked.
Hard rules
- Never echo a live email, phone, national id, or card number.
[REDACTED]only. - Do not build dossiers or export a PII CSV.
- Cap quotes at 12 lines, and strip identifiers from quotes.
Report template
## Lean-privacy (`<mode>`)
**Systems:** <app/logs> | **Budget:** files_read=<n>
| Sev | Location | Kind | Fix |
|-----|----------|------|-----|
| HIGH | file:line | email in logs | drop field; hash if needed for support |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
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.