All skills
rohitg00 avatar

/forget

@a2a2af9
by Rohit Ghumarerohitg00/agentmemory29k stars
2,536

Delete specific observations from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub specific data for privacy.

Use this Skill: https://skilld.dev/gh/rohitg00/agentmemory/forget

This session only. Nothing lands on disk.

EXAMPLES.md

≈364 tokens on demand. Your agent reads this file only when SKILL.md points to it.

forget worked examples

1. Delete a leaked secret

User: "Forget that note where I pasted the API key."

Search:

memory_smart_search { "query": "api key", "limit": 20 }

Response:

{
  "results": [
    { "id": "abc12345", "sessionId": "7f3a9c21", "title": "Pasted staging API key",
      "narrative": "STAGING_KEY=sk-live-..." }
  ]
}

Present and gate:

Found 1 match:

  • abc12345 (session 7f3a9c2) "Pasted staging API key"

Delete this memory? (yes/no)

After the user says yes:

memory_governance_delete { "memoryIds": ["abc12345"], "reason": "user privacy request" }

Response:

{ "deleted": 1 }

Present:

Deleted 1 memory (abc12345).

2. Drop a whole session's observations

User: "Delete everything from the throwaway spike session."

Search, identify the session, then collect every memory id in it:

memory_smart_search { "query": "spike prototype throwaway", "limit": 20 }

Response has 4 results all with sessionId: c98f1100. Show all four, get a yes, then pass every id:

memory_governance_delete {
  "memoryIds": ["m1", "m2", "m3", "m4"],
  "reason": "drop throwaway spike session"
}

Never send { "sessionId": "c98f1100" }; the MCP deletes by memory id only.

3. User declines

User: "Actually, on second thought, keep them."

Do not call delete. Confirm:

Understood, nothing deleted. The 4 memories from session c98f110 are intact.

Source: SKILL.md on GitHub

No alerts17d4 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    The skill allows for deleting specific agent memories after explicit user confirmation. It is generally safe but carries an inherent risk of indirect prompt injection from processing stored data, which is mitigated by strict requirements to show matches and obtain user confirmation before any destructive action is taken.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at a2a2af9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 17 minutes ago.

Activeupdated 2 months ago
argument-hint
[what to forget - session ID, file path, or search term]
user-invocable
true

README badge

README badge for rohitg00/agentmemory/forget