agentleFS
Wsh7AshWsh7Ash/skillmcp/skills/data-retention-policy/SKILL.md

data-retention-policy

Skill0 starsChanged 15 days agoMITView on GitHub

Decide how long tool inputs, outputs and logs live, and make deletion real rather than implied. Use when the server stores captures, findings or credentials-adjacent data

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify deletion removes the bytes rather than only the index entry

    line 23
  2. Distinctive:

    Document the periods where a reviewer can find them

    line 24
  3. Distinctive:

    no orphaned file remains after a retention sweep

    line 32
  4. Distinctive:

    every artifact class has an enforced retention period

    line 62

≈ “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

Data Retention Policy

Decide how long tool inputs, outputs and logs live, and make deletion real rather than implied

Use when: the server stores captures, findings or credentials-adjacent data

Avoid when: the server keeps nothing beyond process memory

Procedure

  1. List every artifact the server writes and where
  2. Assign each a retention period based on the engagement rules
  3. Implement deletion for the shortest-lived class first
  4. Verify deletion removes the bytes rather than only the index entry
  5. Document the periods where a reviewer can find them
  6. Re-test deletion after any change to the storage layout

Signals

  • each stored artifact class has a stated period
  • deletion removes files, not only references
  • the documented periods match the implementation
  • no orphaned file remains after a retention sweep

Patterns

1. Artifact classes

logs: 30 days, captures: engagement end, indexes: ephemeral

2. Real delete

unlink the file and confirm the path is gone

3. Documented

retention table in SECURITY.md

Pitfalls

  • Deleting the index entry while the file remains on disk
  • Keeping captures indefinitely because they were useful once
  • Documenting a period that no code enforces

Done when

  • every artifact class has an enforced retention period
  • deletion is verified at the filesystem level

References

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.