pantheon-search

pantheon-search is a command for Claude Code from ils15/pantheon-legacy. It costs 41 tokens per session (445 once invoked), scanned A, original, MIT.

A command for searching saved agent memories using words or related meaning, with optional namespace and result limits. It can also show memory statistics.

In plain words
What is it for?
Searching memories such as project decisions, session notes, and bug patterns, or viewing memory counts and statistics.
Why use it?
It helps developers find past decisions and work notes without knowing the exact wording used when they were saved.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: agent in frontmatter.

Good fit Searching memories such as project decisions, session notes, and bug patterns, or viewing memory counts and statistics.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ils15/pantheon-legacy/pantheon-search
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.

Clone the repo
git clone --depth 1 https://github.com/ils15/pantheon-legacy

Made for: Claude Code.

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 pantheon-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/ils15/pantheon-legacy/pantheon-search/github.svg)](https://agentmods.dev/commands/ils15/pantheon-legacy/pantheon-search)
Your own site
<a href="https://agentmods.dev/commands/ils15/pantheon-legacy/pantheon-search"><img src="https://agentmods.dev/badge/commands/ils15/pantheon-legacy/pantheon-search/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.

agentmods 80×15 button for pantheon-search

Your own site · 80×15
<a href="https://agentmods.dev/commands/ils15/pantheon-legacy/pantheon-search"><img src="https://agentmods.dev/badge/commands/ils15/pantheon-legacy/pantheon-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.00445
Opus 5 $0.00020 $0.00222
Sonnet 5 $0.00008 $0.00089
Haiku 4.5 $0.00004 $0.00044

Measured 7d ago against content hash e7e947d62e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pantheon-search 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.

commands/pantheon-search.md · 49 lines

What it actually says

What: Searches memory entries via memory_search() with hybrid vector + keyword (RRF fusion). Supports namespace filter, result limit, and stats view.

Usage

/pantheon-search "FastAPI performance"                             → Busca em todos os namespaces
/pantheon-search "FastAPI" --namespace=decisions                    → Busca só em decisions
/pantheon-search "bug pattern" --namespace=sessions --top=10        → 10 resultados
/pantheon-search --stats                                            → memory_stats() completo
/pantheon-search --stats --namespace=decisions                       → Stats por namespace

Flags

Flag Default Descrição
--namespace=<ns> all Filtrar por namespace específico
--top=<N> 5 Número de resultados (max 50)
--stats off Mostrar estatísticas em vez de buscar
🔍 Memory Search: "FastAPI performance"

Results (namespace: all):
  #1 │ decisions │ "Decisão: usar FastAPI..." │ score: 0.89 │ 2026-07-20
  #2 │ repo      │ "FastAPI async patterns"  │ score: 0.74 │ 2026-07-18
  #3 │ sessions  │ "FastAPI migration done"  │ score: 0.61 │ 2026-07-15

Found 3 results in 2 namespaces (0.23s)

Output (stats)

📊 Memory Stats
Total entries: 142
Namespaces: decisions (58), sessions (44), repo (28), default (12)
Vector entries: 142
DB size: 1.2 MB
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. 7d ago First seen · 49 lines · 41 tokens per session scan A e7e947d62e50

Subscribe to this mod's changes

pantheon-search 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 445 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.