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 commands/zircote/subcog/promptsgit clone --depth 1 https://github.com/zircote/subcogWrote 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/zircote/subcog/prompts)<a href="https://agentmods.dev/commands/zircote/subcog/prompts"><img src="https://agentmods.dev/badge/commands/zircote/subcog/prompts.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 | $0.00008 | $0.00679 |
| Opus 5 | $0.00004 | $0.00340 |
| Sonnet 5 | $0.00002 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
prompts 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/subcog:prompts
Access and use pre-defined prompt templates for common memory operations.
Usage
/subcog:prompts --list
/subcog:prompts tutorial [--focus capture|recall|namespaces|workflows]
/subcog:prompts capture-assistant
/subcog:prompts document-decision "Use PostgreSQL for storage"
/subcog:prompts search-help "find authentication patterns"
/subcog:prompts review [--namespace decisions] [--action summarize]
Available Prompts
Prompt Details
tutorial
Arguments:
--focus: Topic to focus on (overview, capture, recall, namespaces, workflows, best-practices)--familiarity: Your experience level (beginner, intermediate, advanced)
Example:
/subcog:prompts tutorial --focus capture --familiarity intermediate
capture-assistant
Process:
- Reviews recent conversation context
- Identifies potential memories (decisions, learnings, patterns)
- Suggests namespace and content for each
- Uses AskUserQuestion to confirm captures
document-decision
Arguments:
decision(required): Brief description of the decisionalternatives(optional): Other options considered
Example:
/subcog:prompts document-decision "Use PostgreSQL" --alternatives "MySQL, SQLite"
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 · 106 lines · 8 tokens per session scan A 8bd3600141b2
prompts is a command published in the GitHub repository zircote/subcog (28 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 679 once invoked, about $0.0000 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 commands, from other repositories
compress
Save this Claude Code session to the vault and update the semantic memory index.
memory-list
DEPRECATED: Use Serena listmemories instead. Lists recent memories from Forgetful with optional project filtering.
preserve
Scan this conversation and silently save anything worth permanent memory.
memcord-save
Save current conversation to memory.
memcord-import
Import content from files/URLs.
memcord-merge
Merge multiple memory slots with duplicate detection.