forget

forget is a command for coding agents from RashadAnsari/myagents. It costs 10 tokens per session (546 once invoked), scanned A, original, MIT.

A command for searching the agent's stored project and user memories and removing entries related to a supplied description.

In plain words
What is it for?
It is for forgetting matching memories, including project-specific practices or personal preferences, after checking both memory stores.
Why use it?
It helps remove outdated or unwanted remembered information instead of leaving it available for future work.

Command

Part of the albino plugin — 8 skills, 9 commands, 13 agents, 3 MCP servers shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/rashadansari/myagents/forget
Clone the repo
git clone --depth 1 https://github.com/RashadAnsari/myagents

Or install albino, the plugin that ships this one along with the rest of its 8 skills, 9 commands, 13 agents, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for forget

README.md
[![agentmods](https://agentmods.dev/badge/commands/rashadansari/myagents/forget.svg)](https://agentmods.dev/commands/rashadansari/myagents/forget)
Your own site
<a href="https://agentmods.dev/commands/rashadansari/myagents/forget"><img src="https://agentmods.dev/badge/commands/rashadansari/myagents/forget.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00546
Opus 5 $0.00005 $0.00273
Sonnet 5 $0.00002 $0.00109
Haiku 4.5 $0.00001 $0.00055

Measured 5d ago against content hash 8139a4f7311e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/albino/commands/forget.md · 70 lines

What it actually says

Task

Search agent memory and forget every entry that matches.

Subject: $ARGUMENTS

Step 1: Validate input

If $ARGUMENTS is empty or missing, stop immediately and tell the user:

Usage: /forget <what to forget>
Example: /forget my preference for two-space indentation
Example: /forget the Prisma migration workflow

Step 2: Get the project root

Run:

git rev-parse --show-toplevel

Store as PROJECT_ROOT.

Step 3: Search both memory stores in parallel

Run both at the same time:

  1. project_search (agent-memory MCP server) with project_root: PROJECT_ROOT, query: $ARGUMENTS, k: 10
  2. user_search (agent-memory MCP server) with query: $ARGUMENTS, k: 10

After results arrive, filter each list: keep only entries whose content is meaningfully related to $ARGUMENTS. Discard unrelated results that surfaced only because of distant semantic similarity.

Store the filtered results as PROJECT_MATCHES and USER_MATCHES.

Step 4: Handle no matches

If both lists are empty after filtering, stop and tell the user:

No memory found matching: <$ARGUMENTS>

Step 5: Forget all matches

Immediately forget every entry in PROJECT_MATCHES and USER_MATCHES without asking for confirmation.

For each project memory, call project_forget (agent-memory MCP server) with:

  • project_root: PROJECT_ROOT
  • id: numeric id of the entry
  • hard_delete: false (soft-delete; reversible)

For each user memory, call user_forget (agent-memory MCP server) with:

  • id: numeric id of the entry
  • hard_delete: false

Run all forget calls in parallel.

Step 6: Report

Tell the user how many memories were forgotten and list their summaries. Mention that the deletions are soft (reversible via project_update archive:false or user_update archive:false) unless the user requests permanent removal.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 70 lines · 10 tokens per session scan A 8139a4f7311e

Subscribe to this mod's changes

forget is a command published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 28d ago), licensed MIT. It adds 10 tokens to every session and 546 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.