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.
npx agentmods add skills/skynetcmd/m3-memory/m3-forgetnpx skills add skynetcmd/m3-memory --skill m3-forgetgit clone --depth 1 https://github.com/skynetcmd/m3-memoryWrote 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.
[](https://agentmods.dev/skills/skynetcmd/m3-memory/m3-forget)<a href="https://agentmods.dev/skills/skynetcmd/m3-memory/m3-forget"><img src="https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-forget.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.00239 |
| Opus 5 | $0.00008 | $0.00120 |
| Sonnet 5 | $0.00003 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
m3-forget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
M3 Forget
When to Use
Use this skill when the user wants to delete a specific memory from their store. Always verify and confirm the deletion to prevent accidental loss of important information.
Instructions
Confirm before delete
Step 1 — fetch the target via m3:memory_get with id="$ARGUMENTS". Show the user:
About to delete:
id: <uuid>
title: <title>
type: <type>
content: <first 200 chars>
Step 2 — ask: "Type the first 8 chars of the id to confirm deletion, anything else to abort."
Step 3 — on match, call m3:memory_delete with the full id. On mismatch, abort and say "skipped — id mismatch."
If the user wants a softer alternative, mention m3:gdpr_forget (Article 17 — sets a tombstone instead of hard delete) or just writing a superseding memory via /m3:save.
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.
- 6d ago First seen · 28 lines · 16 tokens per session scan A 2ebdd9cce35e
m3-forget is a skill published in the GitHub repository skynetcmd/m3-memory (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 16 tokens to every session and 239 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 2026-08-30.
Other skills, from other repositories
hermes3000-writing
Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API. Use for novels, fiction series, nonfiction books, whitepapers, long reads, chapter outlines, character/world-building, style guides, consistency memory, and DOCX/PDF/EPUB/HTML…
zettelkasten
Maintain a Luhmann-style Zettelkasten. Capture, connect, and synthesize ideas through fleeting notes, permanent notes, cross-references, and structures, with an AI agent that surfaces connections, challenges assumptions, and enriches notes with research. Use when the user shares an idea, observation, or inspiration…
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
google-ads
Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.
hue
Read and control Philips Hue Bridge lighting installations through local CLIP v2 or the Hue Remote API with SecretRef-backed credentials and guarded lighting changes.
fronius
Read Fronius photovoltaic inverter data through the local Fronius Solar API V1 or Solar.web Query API cloud, without exposing access-key material.