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/opensesh/karimo-overview/bos-learngit clone --depth 1 https://github.com/opensesh/karimo-overviewWrote 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/opensesh/karimo-overview/bos-learn)<a href="https://agentmods.dev/commands/opensesh/karimo-overview/bos-learn"><img src="https://agentmods.dev/badge/commands/opensesh/karimo-overview/bos-learn.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 5.1 | $0.00000 | $0.00672 |
| Opus 5 | $0.00000 | $0.00336 |
| Sonnet 5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
bos-learn 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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bos-learn - Add Manual Memory
Add a memory manually to the BOS self-evolving memory system.
Usage
/bos-learn <category> "title" "content"
Arguments
| Argument | Description |
|---|---|
category |
Memory category (see below) |
title |
Short descriptive title (max 50 chars) |
content |
The memory to add (can be multi-sentence) |
Categories
| Category | Use For |
|---|---|
entities |
People, services, APIs, external systems |
patterns |
Recurring solutions and best practices |
preferences |
User choices and project conventions |
events |
Significant milestones or decisions |
cases |
Bug fixes, edge cases, anti-patterns |
profile |
Meta-learnings about the user/project |
Examples
/bos-learn patterns "Debug Supabase RLS via JWT" "When debugging Supabase RLS, always check JWT claims first"
/bos-learn preferences "Explicit error messages" "User prefers explicit error messages over generic ones"
/bos-learn cases "useFormStatus requires form" "React 19 useFormStatus must be called inside a form component"
/bos-learn entities "Vercel MCP server" "Vercel MCP server handles deployments and logs"
Behavior
- Parse the category, title, and content from the command
- Check for similar existing memories (deduplication threshold: 0.85)
- If unique, add to the appropriate memory category
- Update the category index.md file
- Report success or explain why it was skipped
Implementation
Execute this command to add the memory:
bunx tsx .bos/lib/memory-manager.ts add <category> "<title>" "<content>"
The memory-manager CLI will:
- Generate embeddings for deduplication
- Check for similar memories
- Add to SQLite database
- Update the markdown index file
Example Output
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.
- 6d ago First seen · 103 lines · 0 tokens per session scan A 1b4863a0ae35
bos-learn is a command published in the GitHub repository opensesh/karimo-overview (11 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 672 tokens. 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
context
项目上下文管理：初始化 .context 目录、记录决策日志、压缩归档、查看历史.
cozempic
Diagnose and prune bloated Claude Code context. Run to slim down the current session before compacting or resuming.
dashboard
Phase 3 monitoring — System health, execution insights, and velocity analytics.
merge
Consolidate feature branch changes and create final PR to main. This completes the v5.0 feature branch workflow after all task PRs have been merged.
run
Execute an approved PRD using feature branch workflow (v7.0). This command generates briefs, auto-reviews them, allows user iteration, and then orchestrates execution.
greptile-review
Execute the full Greptile review cycle on a PR, looping until score meets threshold or circuit breaker triggers.