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/the-essential/reliquery/forgetnpx skills add the-essential/reliquery --skill forgetgit clone --depth 1 https://github.com/the-essential/reliqueryWrote 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/the-essential/reliquery/forget)<a href="https://agentmods.dev/skills/the-essential/reliquery/forget"><img src="https://agentmods.dev/badge/skills/the-essential/reliquery/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 | $0.00131 | $0.01865 |
| Opus 5 | $0.00066 | $0.00932 |
| Sonnet 5 | $0.00026 | $0.00373 |
| Haiku 4.5 | $0.00013 | $0.00186 |
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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Forget is the inverse of memorize — the controlled demolition pipeline. Where memorize consecrates relics into searchable memory, forget removes those entries so they can no longer surface. It handles rollbacks, stale-entry cleanup, re-indexing resets, and deliberate purges.
Deletion in the palace is permanent and irreversible. There is no undo, no recycle bin, no recovery short of re-running memorize from the source vault files. Forget treats that weight seriously: it never deletes without first showing the user the exact drawers it intends to remove, and it never executes without explicit confirmation.
There are four input modes:
- Entity mode: Delete all drawers sourced from specific named relics
- Session mode: Delete drawers added during a recent chronicle or memorize pass
- Stale mode: Find and remove drawers outdated relative to current vault files
- Erase mode: Delete palace drawers and their source vault files from disk — a full purge from both memory layers. Only by explicit user request; never inferred.
Phase 1 — Identify Scope
1a — Load the palace
Call mempalace_status to confirm the system is live. Note the total drawer count for the target wing — you'll compare this against the post-deletion count to verify.
1b — Identify wing
Never run unscoped operations across the full palace. Confirm which wing before searching.
1c — Determine mode and scope
Entity mode — User names specific entities:
- Run
mempalace_search(query="[entity name]", wing="[wing]", limit=20)for each - Check adjacent entities that might share drawers (e.g., a faction file listing the entity as a member)
- Collect all drawer IDs sourced from the target files
Session mode — Deleting a recent batch:
- Call
mempalace_list_drawers(wing="[wing]", limit=100, offset=[total - estimated_count])to retrieve the tail of the drawer list (most recently added) - Cross-reference against known source files from the session
- Paginate backward if needed
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.
- 5d ago First seen · 161 lines · 131 tokens per session scan A cfe2e2abb2d1
forget is a skill published in the GitHub repository the-essential/reliquery (5 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 1,865 once invoked, about $0.0007 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.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
cognee-cli
Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.
cognee-install
Use when the user wants to install cognee and run their first remember → recall flow with the Python SDK — fresh setup, virtual env, extras selection, or a minimal working example.
cognee-server
Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.