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/attckdigital/smith/smith-banknpx skills add ATTCKDigital/smith --skill smith-bankgit clone --depth 1 https://github.com/ATTCKDigital/smithWrote 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/attckdigital/smith/smith-bank)<a href="https://agentmods.dev/skills/attckdigital/smith/smith-bank"><img src="https://agentmods.dev/badge/skills/attckdigital/smith/smith-bank.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 | $0.00054 | $0.01516 |
| Opus 5 | $0.00027 | $0.00758 |
| Sonnet 5 | $0.00011 | $0.00303 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
smith-bank 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smith Idea Bank
Capture ideas mid-conversation and store them in the vault for later processing. The bank is a section of the vault where ideas get deposited for safekeeping until you're ready to withdraw them.
Arguments: $ARGUMENTS
Vault Logging
Log significant events to the vault session log. Read the session log path from .smith/vault/.current-session. If missing, skip logging silently.
Append entries using this format:
### [HH:MM:SS] /smith-bank <event>
**User Request:**
> <verbatim user message or idea description that triggered this action>
**Action:** <banked|listed|processed|edited|removed|prioritized>
**Bank ID:** <BANK-NNN>
**Title:** <idea title>
**Outcome:** <what happened>
**Systems affected:** <system IDs>
Behavior
No Arguments — Bank an Idea
When invoked with no arguments (or via natural language trigger), capture the current conversation's idea:
- Analyze the conversation to understand the idea being banked — what it is, how it came up, what problem it solves, and any initial requirements discussed
- Auto-detect systems the idea would likely impact by scanning
.specify/systems/system-*/spec.mddescriptions against the idea content. Setprimary_systemandalso_affects. - Determine next bank ID by scanning
.smith/vault/bank/for existing files. Extract the highestBANK-NNNfrom frontmatterid:fields, then increment. Start at BANK-001 if none exist. - Generate the bank file at
.smith/vault/bank/YYYY-MM-DD_HHMMSS-<slug>.mdwith this format:
---
id: BANK-NNN
title: "<concise title>"
created: "YYYY-MM-DDTHH:MM:SS"
source_session: "<current session log filename>"
primary_system: "<detected system or 'unassigned'>"
also_affects: []
status: banked
priority: medium
---
# <Title>
## Origin
<2-3 sentences describing the conversation context that led to this idea — what were we working on, what triggered the thought, why it seemed worth saving>
## Idea
<Clear description of the feature or improvement, written with enough detail that someone reading this cold could understand what to build>
## Requirements (Draft)
<Bullet points capturing any requirements that were discussed, even loosely. Include edge cases or constraints mentioned>
## Systems Affected
- **Primary:** <system name and why>
- **Also affects:** <other systems and why, or "none identified">
## Open Questions
<Any obvious questions that would need answering before this could be built. Pre-populate with the most important unknowns based on the conversation>
## Conversation Reference
Session: <link to vault session log>
Approximate timestamp: <when in the session this idea came up>
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.
- 4d ago First seen · 153 lines · 54 tokens per session scan A d7bf0b26477e
smith-bank is a skill published in the GitHub repository ATTCKDigital/smith (52 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,516 once invoked, about $0.0003 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…