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/michaeljauk/brain-starter/save-answernpx skills add michaeljauk/brain-starter --skill save-answergit clone --depth 1 https://github.com/michaeljauk/brain-starterWrote 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/michaeljauk/brain-starter/save-answer)<a href="https://agentmods.dev/skills/michaeljauk/brain-starter/save-answer"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/save-answer.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 | $0.00057 | $0.01007 |
| Opus 5 | $0.00028 | $0.00504 |
| Sonnet 5 | $0.00011 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
save-answer 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Answer
Files a conversation output back into the brain vault. Turns ephemeral Q&A, research, analysis, and comparisons into persistent, cross-linked knowledge.
Inspired by Karpathy's LLM Wiki pattern: "good answers should be filed back into the wiki as new pages so explorations compound."
Trigger phrases
/save-answer- "save this answer"
- "file this"
- "keep this in the brain"
- "this is worth saving"
- "persist this"
Input
The content to save. This can be:
- Explicit: User says "save this" after a Q&A exchange or analysis
- Implicit: User invokes
/save-answerand Claude identifies the most recent substantial output in the conversation
If no clear output is identifiable, ask: "Which part of our conversation should I save?"
Step-by-step workflow
1. Identify the output
Extract the valuable content from the conversation. Common types:
- Research finding -- answer to a question that required multi-source synthesis
- Comparison/analysis -- a table or structured evaluation of options
- Framework application -- a mental model applied to a specific problem
- Decision rationale -- reasoning behind a choice (if not already logged as a decision)
- Technical insight -- something learned about a tool, API, or system
2. Determine placement
| Type | Location |
|---|---|
| Project-specific insight | Append to projects/{project}/{relevant-file}.md |
| Research finding | research/{topic}/{descriptive-slug}.md |
| Cross-project analysis | research/{topic}/{descriptive-slug}.md |
| Decision rationale | decisions/YYYY-MM-DD-{slug}.md (use decision template) |
Check for existing notes on the same topic before creating new files. Update if a close match exists.
3. Write the content
For new notes:
---
title: "{Descriptive title}"
date: YYYY-MM-DD
type: note
tags: [{relevant, tags}]
source: "conversation"
---
# {Descriptive title}
> Derived from conversation on YYYY-MM-DD
## Context
{1-2 sentences: what question or analysis led to this}
## Key Findings
{The actual content -- distilled, not a transcript dump:
- Lead with conclusions
- Include specific data, comparisons, or frameworks
- Keep it scannable}
## Relevance
- [[project-or-note]] -- {how it connects}
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 · 131 lines · 57 tokens per session scan A 9a00ec7c04a0
save-answer is a skill published in the GitHub repository michaeljauk/brain-starter (5 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 1,007 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 2026-08-31.
Other skills, from other repositories
log
Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.
analyse-call
Use this when a local call transcript or meeting note should be analyzed into traceable PersonalOS context. Preserves the source, separates evidence from interpretation, updates only proven owner truth, routes confirmed commitments through task-manager, and never sends messages or triggers external actions without…
remember
Capture knowledge to your Second Brain when triggered by "remember this", "save this", or "brain dump".
remember:evolve
Evolve the brain — consolidate entities, reflect on beliefs, promote top beliefs to Persona. Run weekly or on demand.
remember:process
Process unprocessed Claude Code sessions into your Second Brain.
pkm-explore
Use when researching what the vault knows about a topic — performs graph + semantic exploration with gap analysis to map existing knowledge and find missing connections. Primarily used via the vault-explorer agent. Not for routine session-start context loading (hooks handle that).