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.
git clone --depth 1 https://github.com/ils15/pantheon-legacyWrote 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/commands/ils15/pantheon-legacy/pantheon-forget)<a href="https://agentmods.dev/commands/ils15/pantheon-legacy/pantheon-forget"><img src="https://agentmods.dev/badge/commands/ils15/pantheon-legacy/pantheon-forget/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ils15/pantheon-legacy/pantheon-forget"><img src="https://agentmods.dev/badge/commands/ils15/pantheon-legacy/pantheon-forget.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.00608 |
| Opus 5 | $0.00020 | $0.00304 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
pantheon-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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pantheon-forget — Memory Range Compression
What: Applies range compression to old memory entries — groups entries by time period and namespace, generates a concise summary via fast LLM, replaces N raw entries with 1 summary. Companion to memory_consolidate (merge) vs memory_forget (compress).
Usage
/pantheon-forget → Lista candidatas (7+ dias, modo interativo)
/pantheon-forget --days=30 → Só entradas com 30+ dias
/pantheon-forget --namespace=sessions → Namespace específico
/pantheon-forget --namespace=sessions --days=14 Combinado
/pantheon-forget --auto → Comprime sem confirmação
/pantheon-forget --auto --days=30 --compress → Agressivo: 30+ dias + comprimir em 1 arquivo
/pantheon-forget --dry-run → Preview sem modificar
Flags
| Flag | Default | Descrição |
|---|---|---|
--days=<N> |
7 |
Idade mínima em dias |
--namespace=<ns> |
all |
Namespace específico |
--auto |
off | Comprimir sem confirmação |
--dry-run |
off | Preview sem modificar |
--compress |
off | Comprimir tudo em 1 único entry (modo agressivo) |
How It Works
memory_list()→ obtém entradas, filtra por idade- Agrupa por namespace + mês
- Cada grupo: envia para LLM fast com prompt:
Summarize these N memory entries into 2-3 sentences: [entries...] - Substitui grupo por entry único com key
compressed:<namespace>:<YYYY-MM> - Entradas originais são deletadas via
memory_forget()
Output
🗜️ Memory Range Compression
Group: sessions · 2026-06 (15 entries · 1.2K tokens)
→ "Sessões de junho focadas em migração FastAPI, ajustes de rota e correção de testes."
→ Compressed: 15 → 1 entry ✅
Group: decisions · 2026-05 (8 entries · 640 tokens)
→ "Decisões de maio sobre arquitetura: monorepo mantido, SQLAlchemy 2.0 como padrão."
→ Compressed: 8 → 1 entry ✅
Summary: 2 groups compressed, 23 entries → 2 entries (-91%)
Tokens saved: ~1.8K
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.
- 7d ago First seen · 59 lines · 41 tokens per session scan A a4b82c76a145
pantheon-forget is a command published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 608 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.